6 papers
MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence
Xingyilang Yin, Chengzhengxu Li, Jiahao Chang +2
Humans are born with vision-based 4D spatial-temporal intelligence, which enables us to perceive and reason about the evolution of 3D space over time from purely visual inputs. Des…
GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors
Xingyilang Yin, Qi Zhang, Jiahao Chang +6
Reconstructing 3D scenes using 3D Gaussian Splatting (3DGS) from sparse views is an ill-posed problem due to insufficient information, often resulting in noticeable artifacts. Whil…
Unleashing the Multi-View Fusion Potential: Noise Correction in VLM for Open-Vocabulary 3D Scene Understanding
Xingyilang Yin, Jiale Wang, Xi Yang +3
Recent open-vocabulary 3D scene understanding approaches mainly focus on training 3D networks through contrastive learning with point-text pairs or by distilling 2D features into 3…
SA3DIP: Segment Any 3D Instance with Potential 3D Priors
Xi Yang, Xu Gu, Xingyilang Yin +1
The proliferation of 2D foundation models has sparked research into adapting them for open-world 3D instance segmentation. Recent methods introduce a paradigm that leverages superp…
Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis
Xingyilang Yin, Xi Yang, Liangchen Liu +2
Recently MLP-based methods have shown strong performance in point cloud analysis. Simple MLP architectures are able to learn geometric features in local point groups yet fail to mo…
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation
Mutian Xu, Xingyilang Yin, Lingteng Qiu +3
We introduce SAMPro3D for zero-shot instance segmentation of 3D scenes. Given the 3D point cloud and multiple posed RGB-D frames of 3D scenes, our approach segments 3D instances by…