Maxim
@backpropaganda.bsky.social
Doing Computer Vision stuff with ML.
This is just your standard gradient accumulation?
for i, (input, target) in enumerate(data):
output = model(input)
loss = loss_fn(output, target)
loss = loss / iters_to_accumulate
loss.backward()
if (i + 1) % iters_to_accumulate == 0:
optimizer.zero_grad()
for i, (input, target) in enumerate(data):
output = model(input)
loss = loss_fn(output, target)
loss = loss / iters_to_accumulate
loss.backward()
if (i + 1) % iters_to_accumulate == 0:
optimizer.zero_grad()
December 19, 2024 at 7:02 PM
This is just your standard gradient accumulation?
for i, (input, target) in enumerate(data):
output = model(input)
loss = loss_fn(output, target)
loss = loss / iters_to_accumulate
loss.backward()
if (i + 1) % iters_to_accumulate == 0:
optimizer.zero_grad()
for i, (input, target) in enumerate(data):
output = model(input)
loss = loss_fn(output, target)
loss = loss / iters_to_accumulate
loss.backward()
if (i + 1) % iters_to_accumulate == 0:
optimizer.zero_grad()
PickScan: Object discovery and reconstruction from handheld interactions
(IROS 2024)
tl;dr: an interaction-guided and class-agnostic pipeline for scene reconstruction. The method lets a user move around objects, and outputs the object masks, 3D model and per-frame poses.
(IROS 2024)
tl;dr: an interaction-guided and class-agnostic pipeline for scene reconstruction. The method lets a user move around objects, and outputs the object masks, 3D model and per-frame poses.
November 26, 2024 at 2:02 PM
PickScan: Object discovery and reconstruction from handheld interactions
(IROS 2024)
tl;dr: an interaction-guided and class-agnostic pipeline for scene reconstruction. The method lets a user move around objects, and outputs the object masks, 3D model and per-frame poses.
(IROS 2024)
tl;dr: an interaction-guided and class-agnostic pipeline for scene reconstruction. The method lets a user move around objects, and outputs the object masks, 3D model and per-frame poses.
Vision Foundation Model Enables Generalizable Object Pose Estimation
(Neurips 2024)
tl;dr: The paper explores uses existing foundation models, to elaborate object pose estimation in 2 stages: category-level object viewpoint estimation and object coordinate map estimation.
(Neurips 2024)
tl;dr: The paper explores uses existing foundation models, to elaborate object pose estimation in 2 stages: category-level object viewpoint estimation and object coordinate map estimation.
November 25, 2024 at 2:05 PM
Vision Foundation Model Enables Generalizable Object Pose Estimation
(Neurips 2024)
tl;dr: The paper explores uses existing foundation models, to elaborate object pose estimation in 2 stages: category-level object viewpoint estimation and object coordinate map estimation.
(Neurips 2024)
tl;dr: The paper explores uses existing foundation models, to elaborate object pose estimation in 2 stages: category-level object viewpoint estimation and object coordinate map estimation.