Cédric Rommel
@ccrommel.bsky.social
Research Scientist at Meta | AI and neural interfaces | Interested in data augmentation, generative models, geometric DL, brain decoding, human pose, …
📍Paris, France 🔗 cedricrommel.github.io
📍Paris, France 🔗 cedricrommel.github.io
If you’re at #Neurips2024 next week, come meet us in poster session 3 on Thu 12 Dec 11 a.m!
Or at our oral presentation during the @neur_reps workshop on Saturday 14th!
Paper: arxiv.org/abs/2312.06386
Github: github.com/cedricrommel...
Or at our oral presentation during the @neur_reps workshop on Saturday 14th!
Paper: arxiv.org/abs/2312.06386
Github: github.com/cedricrommel...
December 4, 2024 at 8:00 AM
If you’re at #Neurips2024 next week, come meet us in poster session 3 on Thu 12 Dec 11 a.m!
Or at our oral presentation during the @neur_reps workshop on Saturday 14th!
Paper: arxiv.org/abs/2312.06386
Github: github.com/cedricrommel...
Or at our oral presentation during the @neur_reps workshop on Saturday 14th!
Paper: arxiv.org/abs/2312.06386
Github: github.com/cedricrommel...
While standard approaches directly map 2D coordinates to 3D, prior works noticed that predicted poses’ limbs could shrink and stretch along a movement.
In our work, we prove these are not isolated cases and that these methods always predict *inconsistent* 3D pose sequences.
In our work, we prove these are not isolated cases and that these methods always predict *inconsistent* 3D pose sequences.
December 4, 2024 at 8:00 AM
While standard approaches directly map 2D coordinates to 3D, prior works noticed that predicted poses’ limbs could shrink and stretch along a movement.
In our work, we prove these are not isolated cases and that these methods always predict *inconsistent* 3D pose sequences.
In our work, we prove these are not isolated cases and that these methods always predict *inconsistent* 3D pose sequences.
Inferring 3D human poses from video is highly ill-posed because of depth ambiguity.
Our work accepted to #NeurIPS2024, ManiPose, gets one step closer to solving this, by leveraging prior knowledge about poses topology and cool multiple-choice learning techniques.
Our work accepted to #NeurIPS2024, ManiPose, gets one step closer to solving this, by leveraging prior knowledge about poses topology and cool multiple-choice learning techniques.
December 4, 2024 at 8:00 AM
Inferring 3D human poses from video is highly ill-posed because of depth ambiguity.
Our work accepted to #NeurIPS2024, ManiPose, gets one step closer to solving this, by leveraging prior knowledge about poses topology and cool multiple-choice learning techniques.
Our work accepted to #NeurIPS2024, ManiPose, gets one step closer to solving this, by leveraging prior knowledge about poses topology and cool multiple-choice learning techniques.