TTT3R: 3D Reconstruction as Test-Time Training
Paper
•
2509.26645
•
Published
•
14
Lin Huang
Lin17
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
7 days ago
TTT3R: 3D Reconstruction as Test-Time Training
upvoted
a
paper
7 days ago
MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
upvoted
a
paper
7 days ago
DA^2: Depth Anything in Any Direction
Organizations
None yet
upvoted
17
papers
7 days ago
MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
Paper
•
2509.26391
•
Published
•
20
DA^2: Depth Anything in Any Direction
Paper
•
2509.26618
•
Published
•
25
Triangle Splatting+: Differentiable Rendering with Opaque Triangles
Paper
•
2509.25122
•
Published
•
8
Human3R: Everyone Everywhere All at Once
Paper
•
2510.06219
•
Published
•
9
ShapeGen4D: Towards High Quality 4D Shape Generation from Videos
Paper
•
2510.06208
•
Published
•
18
WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation
Paper
•
2510.07313
•
Published
•
6
SViM3D: Stable Video Material Diffusion for Single Image 3D Generation
Paper
•
2510.08271
•
Published
•
5
Instant4D: 4D Gaussian Splatting in Minutes
Paper
•
2510.01119
•
Published
•
6
InfiniHuman: Infinite 3D Human Creation with Precise Control
Paper
•
2510.11650
•
Published
•
5
FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding
Paper
•
2510.10868
•
Published
•
11
Detect Anything via Next Point Prediction
Paper
•
2510.12798
•
Published
•
42
Learning to Grasp Anything by Playing with Random Toys
Paper
•
2510.12866
•
Published
•
4
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
Paper
•
2510.13778
•
Published
•
16
Trace Anything: Representing Any Video in 4D via Trajectory Fields
Paper
•
2510.13802
•
Published
•
30
Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation
Paper
•
2510.14976
•
Published
•
3
AnyUp: Universal Feature Upsampling
Paper
•
2510.12764
•
Published
•
10
upvoted
3
papers
about 1 month ago