5 papers
UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation
Ping Zhou, Haoyu Wang, Mengmeng Zheng +4
RGB-T semantic segmentation requires strictly aligned VIS-IR-Label triplets; however, such aligned triplet data are often scarce in real-world scenarios. Existing generative augmen…
No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves
Dengyang Jiang, Mengmeng Wang, Liuzhuozheng Li +6
Recent studies have demonstrated that learning a meaningful internal representation can accelerate generative training. However, existing approaches necessitate to either introduce…
JoDiffusion: Jointly Diffusing Image with Pixel-Level Annotations for Semantic Segmentation Promotion
Haoyu Wang, Lei Zhang, Wenrui Liu +3
Given the inherently costly and time-intensive nature of pixel-level annotation, the generation of synthetic datasets comprising sufficiently diverse synthetic images paired with g…
Prompt-Free Conditional Diffusion for Multi-object Image Augmentation
Haoyu Wang, Lei Zhang, Wei Wei +2
Diffusion models has underpinned much recent advances of dataset augmentation in various computer vision tasks. However, when involving generating multi-object images as real scena…
RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation
Mingfei Han, Liang Ma, Kamila Zhumakhanova +5
Vision-and-Language Navigation (VLN) suffers from the limited diversity and scale of training data, primarily constrained by the manual curation of existing simulators. To address…