IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations
Paper
•
2412.12083
•
Published
•
12
Dahua Lin
lindahua
AI & ML interests
Computer Vision, Natual Language Processing, Neural Graphics
Recent Activity
authored
a paper
8 days ago
IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and
Illuminations
authored
a paper
14 days ago
3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video
Generation
Organizations
None yet
lindahua's activity
authored
a
paper
8 days ago
authored
a
paper
12 days ago
authored
2
papers
14 days ago
authored
a
paper
16 days ago
authored
a
paper
20 days ago
authored
a
paper
22 days ago
authored
a
paper
about 1 month ago
authored
4
papers
2 months ago
MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
Paper
•
2410.17637
•
Published
•
34
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
Paper
•
2410.17247
•
Published
•
45
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
Paper
•
2410.16268
•
Published
•
65
LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
Paper
•
2410.09732
•
Published
•
54
authored
3
papers
3 months ago
BroadWay: Boost Your Text-to-Video Generation Model in a Training-free Way
Paper
•
2410.06241
•
Published
•
10
Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate
Paper
•
2410.07167
•
Published
•
37
3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
Paper
•
2409.12957
•
Published
•
18
authored
a
paper
5 months ago
authored
4
papers
6 months ago
VEnhancer: Generative Space-Time Enhancement for Video Generation
Paper
•
2407.07667
•
Published
•
14
Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images
Paper
•
2407.06191
•
Published
•
11
ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models
Paper
•
2407.04693
•
Published
•
1
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
Paper
•
2407.03320
•
Published
•
93