Anh-Quan Cao
@anhquancao.bsky.social
Research Scientist at Valeo.ai.
https://anhquancao.github.io/
https://anhquancao.github.io/
Reposted by Anh-Quan Cao
Congratulations to our lab colleagues who have been named Outstanding Reviewers at #ICCV2025 👏
Andrei Bursuc @abursuc.bsky.social
Anh-Quan Cao @anhquancao.bsky.social
Renaud Marlet
Eloi Zablocki @eloizablocki.bsky.social
@iccv.bsky.social
iccv.thecvf.com/Conferences/...
Andrei Bursuc @abursuc.bsky.social
Anh-Quan Cao @anhquancao.bsky.social
Renaud Marlet
Eloi Zablocki @eloizablocki.bsky.social
@iccv.bsky.social
iccv.thecvf.com/Conferences/...
2025 ICCV Program Committee
iccv.thecvf.com
October 2, 2025 at 3:28 PM
Congratulations to our lab colleagues who have been named Outstanding Reviewers at #ICCV2025 👏
Andrei Bursuc @abursuc.bsky.social
Anh-Quan Cao @anhquancao.bsky.social
Renaud Marlet
Eloi Zablocki @eloizablocki.bsky.social
@iccv.bsky.social
iccv.thecvf.com/Conferences/...
Andrei Bursuc @abursuc.bsky.social
Anh-Quan Cao @anhquancao.bsky.social
Renaud Marlet
Eloi Zablocki @eloizablocki.bsky.social
@iccv.bsky.social
iccv.thecvf.com/Conferences/...
Reposted by Anh-Quan Cao
Very happy that finally - after ~2 years of review - PanopticNERF-360 has been accepted to TPAMI :)
Panoramic 3D-to-2D Label Transfer in Urban Scenes. Kudos to the team and Yiyi Liao for leading the effort. Here is the project page: fuxiao0719.github.io/projects/pan...
Panoramic 3D-to-2D Label Transfer in Urban Scenes. Kudos to the team and Yiyi Liao for leading the effort. Here is the project page: fuxiao0719.github.io/projects/pan...
June 24, 2025 at 2:39 PM
Very happy that finally - after ~2 years of review - PanopticNERF-360 has been accepted to TPAMI :)
Panoramic 3D-to-2D Label Transfer in Urban Scenes. Kudos to the team and Yiyi Liao for leading the effort. Here is the project page: fuxiao0719.github.io/projects/pan...
Panoramic 3D-to-2D Label Transfer in Urban Scenes. Kudos to the team and Yiyi Liao for leading the effort. Here is the project page: fuxiao0719.github.io/projects/pan...
Reposted by Anh-Quan Cao
Since we went public a year ago, more than 1.6 mio articles have been read via our paper recommendation platform www.scholar-inbox.com. Super proud of the team!
Teaser: Something BIG is coming up soon .. stay tuned!
Teaser: Something BIG is coming up soon .. stay tuned!
April 1, 2025 at 12:45 PM
Since we went public a year ago, more than 1.6 mio articles have been read via our paper recommendation platform www.scholar-inbox.com. Super proud of the team!
Teaser: Something BIG is coming up soon .. stay tuned!
Teaser: Something BIG is coming up soon .. stay tuned!
Reposted by Anh-Quan Cao
🚀 Names matter! We show that better class names in open-vocabulary segmentation benchmarks greatly improve dataset quality and boost model performance. RENOVATE your dataset labels with our automatic framework! #AI #ComputerVision #NeurIPS24
andrehuang.github.io/renovate/
andrehuang.github.io/renovate/
February 26, 2025 at 2:45 PM
🚀 Names matter! We show that better class names in open-vocabulary segmentation benchmarks greatly improve dataset quality and boost model performance. RENOVATE your dataset labels with our automatic framework! #AI #ComputerVision #NeurIPS24
andrehuang.github.io/renovate/
andrehuang.github.io/renovate/
Reposted by Anh-Quan Cao
Our beginner's oriented accessible introduction to modern deep RL is now published in Foundations and Trends in Optimization. It is a great entry to the field if you want to jumpstart into RL!
@bernhard-jaeger.bsky.social
www.nowpublishers.com/article/Deta...
arxiv.org/abs/2312.08365
@bernhard-jaeger.bsky.social
www.nowpublishers.com/article/Deta...
arxiv.org/abs/2312.08365
February 22, 2025 at 7:32 PM
Our beginner's oriented accessible introduction to modern deep RL is now published in Foundations and Trends in Optimization. It is a great entry to the field if you want to jumpstart into RL!
@bernhard-jaeger.bsky.social
www.nowpublishers.com/article/Deta...
arxiv.org/abs/2312.08365
@bernhard-jaeger.bsky.social
www.nowpublishers.com/article/Deta...
arxiv.org/abs/2312.08365
Reposted by Anh-Quan Cao
Replace "github" with "gitingest" in the url, and you get the whole repo as a single string that you can then paste in your LLMs
February 14, 2025 at 3:12 AM
Replace "github" with "gitingest" in the url, and you get the whole repo as a single string that you can then paste in your LLMs
Reposted by Anh-Quan Cao
Thrilled to announce our workshop on Embodied Intelligence for Autonomous Systems on the Horizon @cvprconference.bsky.social featuring a crazy line-up of speakers and challenges.
Mark it in your agendas and also in your registration #cvpr2025
opendrivelab.com/cvpr2025/wor...
Mark it in your agendas and also in your registration #cvpr2025
opendrivelab.com/cvpr2025/wor...
January 23, 2025 at 9:18 PM
Thrilled to announce our workshop on Embodied Intelligence for Autonomous Systems on the Horizon @cvprconference.bsky.social featuring a crazy line-up of speakers and challenges.
Mark it in your agendas and also in your registration #cvpr2025
opendrivelab.com/cvpr2025/wor...
Mark it in your agendas and also in your registration #cvpr2025
opendrivelab.com/cvpr2025/wor...
Reposted by Anh-Quan Cao
The CUDA programming guide docs.nvidia.com/cuda/cuda-c-... is worth studying, even if you're not programming in CUDA. A lot of this knowledge is transferable to DX12/Vulkan compute shaders, especially the GPU architecture/best practices/performance guidelines parts.
CUDA C++ Programming Guide
The programming guide to the CUDA model and interface.
docs.nvidia.com
January 19, 2025 at 12:26 PM
The CUDA programming guide docs.nvidia.com/cuda/cuda-c-... is worth studying, even if you're not programming in CUDA. A lot of this knowledge is transferable to DX12/Vulkan compute shaders, especially the GPU architecture/best practices/performance guidelines parts.
Reposted by Anh-Quan Cao
Learnings from Scaling Visual Tokenizers for Reconstruction and Generation arxiv.org/abs/2501.09755
The authors study in detail the transition from convolutional backbones to ViT for visual tokenization (ViTok -- excellent name) as well as the impact of scaling up
The authors study in detail the transition from convolutional backbones to ViT for visual tokenization (ViTok -- excellent name) as well as the impact of scaling up
January 19, 2025 at 6:28 AM
Learnings from Scaling Visual Tokenizers for Reconstruction and Generation arxiv.org/abs/2501.09755
The authors study in detail the transition from convolutional backbones to ViT for visual tokenization (ViTok -- excellent name) as well as the impact of scaling up
The authors study in detail the transition from convolutional backbones to ViT for visual tokenization (ViTok -- excellent name) as well as the impact of scaling up
Reposted by Anh-Quan Cao
I wish I stumbled on this pretty and clear intro to CUDA and GPUs years ago : modal.com/gpu-glossary
January 16, 2025 at 8:27 AM
I wish I stumbled on this pretty and clear intro to CUDA and GPUs years ago : modal.com/gpu-glossary
Reposted by Anh-Quan Cao
Excited to share that today our paper recommender platform www.scholar-inbox.com has reached 20k users! We hope to reach 100k by the end of the year.. Lots of new features are being worked on currently and rolled out soon.
January 15, 2025 at 10:03 PM
Excited to share that today our paper recommender platform www.scholar-inbox.com has reached 20k users! We hope to reach 100k by the end of the year.. Lots of new features are being worked on currently and rolled out soon.
Reposted by Anh-Quan Cao
That is to say, I think it makes not much sense to fear what others might do. Do the research that you are interested in and I am sure it will be relevant as you bring a unique perspective to the field.
January 15, 2025 at 8:57 AM
That is to say, I think it makes not much sense to fear what others might do. Do the research that you are interested in and I am sure it will be relevant as you bring a unique perspective to the field.
Reposted by Anh-Quan Cao
Please tell people that they don’t have to stand out to do good work and be respected.
Doing honest research and taking care of your colleagues and your field can be as valuable.
We already have so much anxiety and fomo in the field, I’m not sure it’s making us better.
Doing honest research and taking care of your colleagues and your field can be as valuable.
We already have so much anxiety and fomo in the field, I’m not sure it’s making us better.
🧵 1/3 Many at #CVPR2024 & #ECCV2024 asked what would be next in our workshop series.
We're excited to announce "How to Stand Out in the Crowd?" at #CVPR2025 Nashville - our 4th community-building workshop featuring this incredible speaker lineup!
🔗 sites.google.com/view/standou...
We're excited to announce "How to Stand Out in the Crowd?" at #CVPR2025 Nashville - our 4th community-building workshop featuring this incredible speaker lineup!
🔗 sites.google.com/view/standou...
January 14, 2025 at 6:06 AM
Please tell people that they don’t have to stand out to do good work and be respected.
Doing honest research and taking care of your colleagues and your field can be as valuable.
We already have so much anxiety and fomo in the field, I’m not sure it’s making us better.
Doing honest research and taking care of your colleagues and your field can be as valuable.
We already have so much anxiety and fomo in the field, I’m not sure it’s making us better.
Reposted by Anh-Quan Cao
First, new "How to be a good reviewer? Reviewer Tutorial for CVPR 2025" @cvprconference.bsky.social is amazing!
docs.google.com/presentation...
The thing I don't like - "at least 4 hours if you are not very experienced."
I think, 4 - for the "very experienced", and"not exp" should be 6 at least.
docs.google.com/presentation...
The thing I don't like - "at least 4 hours if you are not very experienced."
I think, 4 - for the "very experienced", and"not exp" should be 6 at least.
How to be a good CVPR 2025 reviewer
How to be a good reviewer? Reviewer Tutorial for CVPR 2025 CVPR 2025 Program Chairs Fuxin Li, Hao Su, Hedvig Kjellström, Phillip Isola, Siyu Tang, Vincent Lepetit [Slides adapted from: Reviewer Slides...
docs.google.com
January 10, 2025 at 9:10 PM
First, new "How to be a good reviewer? Reviewer Tutorial for CVPR 2025" @cvprconference.bsky.social is amazing!
docs.google.com/presentation...
The thing I don't like - "at least 4 hours if you are not very experienced."
I think, 4 - for the "very experienced", and"not exp" should be 6 at least.
docs.google.com/presentation...
The thing I don't like - "at least 4 hours if you are not very experienced."
I think, 4 - for the "very experienced", and"not exp" should be 6 at least.
Reposted by Anh-Quan Cao
The ICCV 2025 website is finally online! 🎉
iccv.thecvf.com
@cvprconference.bsky.social @iccv.bsky.social
@yoshitomo-cs.bsky.social
@csprofkgd.bsky.social
@wjscheirer.bsky.social
iccv.thecvf.com
@cvprconference.bsky.social @iccv.bsky.social
@yoshitomo-cs.bsky.social
@csprofkgd.bsky.social
@wjscheirer.bsky.social
2025 Conference
iccv.thecvf.com
January 10, 2025 at 9:54 PM
The ICCV 2025 website is finally online! 🎉
iccv.thecvf.com
@cvprconference.bsky.social @iccv.bsky.social
@yoshitomo-cs.bsky.social
@csprofkgd.bsky.social
@wjscheirer.bsky.social
iccv.thecvf.com
@cvprconference.bsky.social @iccv.bsky.social
@yoshitomo-cs.bsky.social
@csprofkgd.bsky.social
@wjscheirer.bsky.social
Reposted by Anh-Quan Cao
How do we go beyond colors and recover the intrinsic scene properties? 🤔
👁️ IRIS: Inverse Rendering of Indoor Scenes
IRIS estimates accurate material, lighting, and camera response functions given a set of LDR images, enabling photorealistic and view-consistent relighting and object insertion.
👁️ IRIS: Inverse Rendering of Indoor Scenes
IRIS estimates accurate material, lighting, and camera response functions given a set of LDR images, enabling photorealistic and view-consistent relighting and object insertion.
January 10, 2025 at 9:56 PM
How do we go beyond colors and recover the intrinsic scene properties? 🤔
👁️ IRIS: Inverse Rendering of Indoor Scenes
IRIS estimates accurate material, lighting, and camera response functions given a set of LDR images, enabling photorealistic and view-consistent relighting and object insertion.
👁️ IRIS: Inverse Rendering of Indoor Scenes
IRIS estimates accurate material, lighting, and camera response functions given a set of LDR images, enabling photorealistic and view-consistent relighting and object insertion.
Reposted by Anh-Quan Cao
I have switched from X and Facebook to Bluesky. I will delete both my X and Facebook accounts in a little bit.
January 8, 2025 at 7:38 AM
I have switched from X and Facebook to Bluesky. I will delete both my X and Facebook accounts in a little bit.
Reposted by Anh-Quan Cao
code release for our ECCV paper CarFormer: github.com/Shamdan17/Ca...
Shadi is an amazing coder, so this is a great starting point for privileged agents on CARLA. three versions to play with:
1. BEV quantized with a VQ-VAE
2. Attributes (PlanT)
3. BEV => slots (CarFormer)
Shadi is an amazing coder, so this is a great starting point for privileged agents on CARLA. three versions to play with:
1. BEV quantized with a VQ-VAE
2. Attributes (PlanT)
3. BEV => slots (CarFormer)
GitHub - Shamdan17/CarFormer: The official repository for the ECCV2024 paper "CarFormer: Self-Driving with Learned Object-Centric Representations"
The official repository for the ECCV2024 paper "CarFormer: Self-Driving with Learned Object-Centric Representations" - Shamdan17/CarFormer
github.com
December 28, 2024 at 12:03 PM
code release for our ECCV paper CarFormer: github.com/Shamdan17/Ca...
Shadi is an amazing coder, so this is a great starting point for privileged agents on CARLA. three versions to play with:
1. BEV quantized with a VQ-VAE
2. Attributes (PlanT)
3. BEV => slots (CarFormer)
Shadi is an amazing coder, so this is a great starting point for privileged agents on CARLA. three versions to play with:
1. BEV quantized with a VQ-VAE
2. Attributes (PlanT)
3. BEV => slots (CarFormer)
Reposted by Anh-Quan Cao
My book is (at last) out, just in time for Christmas!
A blog post to celebrate and present it: francisbach.com/my-book-is-o...
A blog post to celebrate and present it: francisbach.com/my-book-is-o...
December 21, 2024 at 3:23 PM
My book is (at last) out, just in time for Christmas!
A blog post to celebrate and present it: francisbach.com/my-book-is-o...
A blog post to celebrate and present it: francisbach.com/my-book-is-o...
Reposted by Anh-Quan Cao
This simple pytorch trick will cut in half your GPU memory use / double your batch size (for real). Instead of adding losses and then computing backward, it's better to compute the backward on each loss (which frees the computational graph). Results will be exactly identical
December 19, 2024 at 4:59 AM
This simple pytorch trick will cut in half your GPU memory use / double your batch size (for real). Instead of adding losses and then computing backward, it's better to compute the backward on each loss (which frees the computational graph). Results will be exactly identical
Reposted by Anh-Quan Cao
At some point, we ‘old’ folks who were there before transformers should just gather and write a long survey about everything that was there before…
A post by @cloneofsimo on Twitter made me write up some lore about residuals, ResNets, and Transformers. And I couldn't resist sliding in the usual cautionary tale about small/mid-scale != large-scale.
Blogpost: lb.eyer.be/s/residuals....
Blogpost: lb.eyer.be/s/residuals....
December 19, 2024 at 9:38 AM
At some point, we ‘old’ folks who were there before transformers should just gather and write a long survey about everything that was there before…
Reposted by Anh-Quan Cao
⚠️Reconstructing sharp 3D meshes from a few unposed images is a hard and ambiguous problem.
☑️With MAtCha, we leverage a pretrained depth model to recover sharp meshes from sparse views including both foreground and background, within mins!🧵
🌐Webpage: anttwo.github.io/matcha/
☑️With MAtCha, we leverage a pretrained depth model to recover sharp meshes from sparse views including both foreground and background, within mins!🧵
🌐Webpage: anttwo.github.io/matcha/
December 11, 2024 at 2:59 PM
⚠️Reconstructing sharp 3D meshes from a few unposed images is a hard and ambiguous problem.
☑️With MAtCha, we leverage a pretrained depth model to recover sharp meshes from sparse views including both foreground and background, within mins!🧵
🌐Webpage: anttwo.github.io/matcha/
☑️With MAtCha, we leverage a pretrained depth model to recover sharp meshes from sparse views including both foreground and background, within mins!🧵
🌐Webpage: anttwo.github.io/matcha/
Reposted by Anh-Quan Cao
How to schedule a meeting?
When you ask for a meeting with others, you are asking for their time. You are asking for their most valuable, finite resource to benefit yourself (e.g., for advice, networking, questions, and opportunities).
Here are some tips that I found useful.
When you ask for a meeting with others, you are asking for their time. You are asking for their most valuable, finite resource to benefit yourself (e.g., for advice, networking, questions, and opportunities).
Here are some tips that I found useful.
December 10, 2024 at 12:02 AM
How to schedule a meeting?
When you ask for a meeting with others, you are asking for their time. You are asking for their most valuable, finite resource to benefit yourself (e.g., for advice, networking, questions, and opportunities).
Here are some tips that I found useful.
When you ask for a meeting with others, you are asking for their time. You are asking for their most valuable, finite resource to benefit yourself (e.g., for advice, networking, questions, and opportunities).
Here are some tips that I found useful.
Reposted by Anh-Quan Cao
📢 𝐏𝐫𝐄𝐝𝐢𝐭𝐨𝐫𝟑𝐃: 𝐅𝐚𝐬𝐭 𝐚𝐧𝐝 𝐏𝐫𝐞𝐜𝐢𝐬𝐞 𝟑𝐃 𝐒𝐡𝐚𝐩𝐞 𝐄𝐝𝐢𝐭𝐢𝐧𝐠 📢
We propose a training-free 3D shape editing approach that rapidly and precisely edits the regions intended by the user and keeps the rest as is.
We propose a training-free 3D shape editing approach that rapidly and precisely edits the regions intended by the user and keeps the rest as is.
December 10, 2024 at 1:06 PM
📢 𝐏𝐫𝐄𝐝𝐢𝐭𝐨𝐫𝟑𝐃: 𝐅𝐚𝐬𝐭 𝐚𝐧𝐝 𝐏𝐫𝐞𝐜𝐢𝐬𝐞 𝟑𝐃 𝐒𝐡𝐚𝐩𝐞 𝐄𝐝𝐢𝐭𝐢𝐧𝐠 📢
We propose a training-free 3D shape editing approach that rapidly and precisely edits the regions intended by the user and keeps the rest as is.
We propose a training-free 3D shape editing approach that rapidly and precisely edits the regions intended by the user and keeps the rest as is.
Reposted by Anh-Quan Cao
📢DNF: Generating 4D animations with dictionary-based neural fields!
Xinyi Zhang presents a new dictionary-based neural field for unconditional 4D generation of deforming shapes -- generating motions with high-quality shape and temporal consistency.
xzhang-t.github.io/project/DNF/
Xinyi Zhang presents a new dictionary-based neural field for unconditional 4D generation of deforming shapes -- generating motions with high-quality shape and temporal consistency.
xzhang-t.github.io/project/DNF/
December 9, 2024 at 2:11 PM
📢DNF: Generating 4D animations with dictionary-based neural fields!
Xinyi Zhang presents a new dictionary-based neural field for unconditional 4D generation of deforming shapes -- generating motions with high-quality shape and temporal consistency.
xzhang-t.github.io/project/DNF/
Xinyi Zhang presents a new dictionary-based neural field for unconditional 4D generation of deforming shapes -- generating motions with high-quality shape and temporal consistency.
xzhang-t.github.io/project/DNF/