10 papers
Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction
Kejun Ren, Lei Jin, Tianxin Huang +2
Streaming 3D reconstruction under a strict constant-memory budget hinges on how the recurrent state is updated as the stream evolves. We profile TTT3R-style per-token gates across…
See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
Dongyue Lu, Ao Liang, Tianxin Huang +8
Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video-to-4D methods typically rely on manually ann…
PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis
Qing Mao, Tianxin Huang, Yu Zhu +3
Pairwise camera pose estimation from sparsely overlapping image pairs remains a critical and unsolved challenge in 3D vision. Most existing methods struggle with image pairs that h…
FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction
Yunsong Wang, Tianxin Huang, Hanlin Chen +1
Recently, the integration of the efficient feed-forward scheme into 3D Gaussian Splatting (3DGS) has been actively explored. However, most existing methods focus on sparse view rec…
Unified Geometry and Color Compression Framework for Point Clouds via Generative Diffusion Priors
Tianxin Huang, Gim Hee Lee
With the growth of 3D applications and the rapid increase in sensor-collected 3D point cloud data, there is a rising demand for efficient compression algorithms. Most existing lear…
ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors
Tianxin Huang, Zhiwen Yan, Yuyang Zhao +1
3D point clouds directly collected from objects through sensors are often incomplete due to self-occlusion. Conventional methods for completing these partial point clouds rely on m…