Search Results for author:
Found 9 papers, 6 papers with code
HoloPart: Generative 3D Part Amodal Segmentation
3D part amodal segmentation--decomposing a 3D shape into complete, semantically meaningful parts, even when occluded--is a challenging but crucial task for 3D content creation and understanding.
Beyond Outcomes: Transparent Assessment of LLM Reasoning in Games
Furthermore, we develop a suite of rule-based algorithms to generate ground truth for these subproblems, enabling rigorous validation of the LLMs' intermediate reasoning steps.
MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
This paper introduces MIDI, a novel paradigm for compositional 3D scene generation from a single image.
Ranked #1 on
Speech Separation
on GRID corpus (mixed-speech)
SAMPart3D: Segment Any Part in 3D Objects
For flexibility, we distill scale-conditioned part-aware 3D features for 3D part segmentation at multiple granularities.
Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images
Afterward, it proceeds to edit the back views.
DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
However, due to the lack of information from multiple views, these works encounter difficulties in generating controllable novel views.
SAM3D: Segment Anything in 3D Scenes
In this work, we propose SAM3D, a novel framework that is able to predict masks in 3D point clouds by leveraging the Segment-Anything Model (SAM) in RGB images without further training or finetuning.
Data-Driven Network Neuroscience: On Data Collection and Benchmark
This paper presents a comprehensive and quality collection of functional human brain network data for potential research in the intersection of neuroscience, machine learning, and graph analytics.
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
To address this issue, we propose CLIP2Point, an image-depth pre-training method by contrastive learning to transfer CLIP to the 3D domain, and adapt it to point cloud classification.
Ranked #3 on
Zero-Shot Transfer 3D Point Cloud Classification
on ModelNet10
(using extra training data)
