11 papers
COSMIO: A Benchmark for Cross-Survey Modality Imputation
Dichang Zhang, Yixuan Shao, Jiaqi Deng +8
Large-scale astronomical surveys define a heterogeneous, partially observed multi-survey learning setting: each object is observed by only a subset of surveys, while survey observa…
TRIG: Toward Measuring Texture Realism in Image Generation
Zhiwei Xu, Jiali Cui, Zhiqiang Lao +2
This paper studies the backbone used by metrics for evaluating the quality of generated images. Although generative models have advanced rapidly, some outputs still exhibit unreali…
LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception
Juyi Lin, Zhiqiang Lao, Jiali Cui +9
Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, whereas uniform temporal compression…
A General-Purpose VLM Can Teach an Astronomy Foundation Model to Better Recognize Galaxy Morphology
Dichang Zhang, Jiaqi Deng, Yixuan Shao +7
Existing astronomy foundation models provide strong galaxy representations, but adapting them to new survey conditions and survey-specific morphology recognition tasks still requir…
ChordVideo: One-Step, Training-Free, Temporally Consistent Video Editing via Low-Energy Transport
Zhiqiang Lao
One-step text-to-image models enable training-free, inversion-free editing with only 1--2 network function evaluations (NFE), while ChordEdit stabilizes such edits through low-ener…
TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion
Nurislam Tursynbek, Zhiqiang Lao, Heather Yu +2
Recent text-to-video diffusion transformers generate visually compelling frames, yet still struggle with temporal coherence, often producing flickering, drifting, or unstable motio…
Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision
Jiali Cui, Zhiqiang Lao, Heather Yu
Energy-based models (EBMs) are a flexible class of deep generative models and are well-suited to capture complex dependencies in multimodal data. However, learning multimodal EBM b…
SIRR-LMM: Single-image Reflection Removal via Large Multimodal Model
Yu Guo, Zhiqiang Lao, Xiyun Song +2
Glass surfaces create complex interactions of reflected and transmitted light, making single-image reflection removal (SIRR) challenging. Existing datasets suffer from limited phys…
Neural Geometry Image-Based Representations with Optimal Transport (OT)
Xiang Gao, Yuanpeng Liu, Xinmu Wang +7
Neural representations for 3D meshes are emerging as an effective solution for compact storage and efficient processing. Existing methods often rely on neural overfitting, where a…
Scene Perceived Image Perceptual Score (SPIPS): combining global and local perception for image quality assessment
Zhiqiang Lao, Heather Yu
The rapid advancement of artificial intelligence and widespread use of smartphones have resulted in an exponential growth of image data, both real (camera-captured) and virtual (AI…
ePBR: Extended PBR Materials in Image Synthesis
Yu Guo, Zhiqiang Lao, Xiyun Song +3
Realistic indoor or outdoor image synthesis is a core challenge in computer vision and graphics. The learning-based approach is easy to use but lacks physical consistency, while tr…