11 papers
SSR: A Training-Free Approach for Streaming 3D Reconstruction
Hui Deng, Yuxin Mao, Yuxin He +1
Streaming 3D reconstruction demands long-horizon state updates under strict latency constraints, yet stateful recurrent models often suffer from geometric drift as errors accumulat…
RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations
Mochu Xiang, Zhelun Shen, Xuesong Li +7
Human perceive the 3D world through 2D observations from limited viewpoints. While recent feed-forward generalizable 3D reconstruction models excel at recovering 3D structures from…
Learning Spatial Decay for Vision Transformers
Yuxin Mao, Zhen Qin, Jinxing Zhou +4
Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases, leading to suboptimal performance on spa…
Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective
Yuxin Mao, Zhen Qin, Jinxing Zhou +6
Autoregressive (AR) models have garnered significant attention in image generation for their ability to effectively capture both local and global structures within visual data. How…
SABER: Spatially Consistent 3D Universal Adversarial Objects for BEV Detectors
Aixuan Li, Mochu Xiang, Bosen Hou +3
Adversarial robustness of BEV 3D object detectors is critical for autonomous driving (AD). Existing invasive attacks require altering the target vehicle itself (e.g. attaching patc…
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Yan Ma, Linge Du, Xuyang Shen +7
Reinforcement learning (RL) is becoming an important direction for post-training vision-language models (VLMs), but public training methodologies for unified multimodal RL remain m…
A Generative Victim Model for Segmentation
Aixuan Li, Jing Zhang, Jiawei Shi +2
We find that the well-trained victim models (VMs), against which the attacks are generated, serve as fundamental prerequisites for adversarial attacks, i.e. a segmentation VM is ne…
Deep Non-rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling
Hui Deng, Jiawei Shi, Zhen Qin +2
Non-Rigid Structure-from-Motion (NRSfM) is a classic 3D vision problem, where a 2D sequence is taken as input to estimate the corresponding 3D sequence. Recently, the deep neural n…
You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet
Zhen Qin, Yuxin Mao, Xuyang Shen +4
Linear attention mechanisms have gained prominence in causal language models due to their linear computational complexity and enhanced speed. However, the inherent decay mechanism…
Non-rigid Structure-from-Motion: Temporally-smooth Procrustean Alignment and Spatially-variant Deformation Modeling
Jiawei Shi, Hui Deng, Yuchao Dai
Even though Non-rigid Structure-from-Motion (NRSfM) has been extensively studied and great progress has been made, there are still key challenges that hinder their broad real-world…
TAVGBench: Benchmarking Text to Audible-Video Generation
Yuxin Mao, Xuyang Shen, Jing Zhang +5
The Text to Audible-Video Generation (TAVG) task involves generating videos with accompanying audio based on text descriptions. Achieving this requires skillful alignment of both a…