Related papers: $\mathtt{M^3VIR}$: A Large-Scale Multi-Modality Mu…
Rain degrades the visual quality of multi-view images, which are essential for 3D scene reconstruction, resulting in inaccurate and incomplete reconstruction results. Existing datasets often overlook two critical characteristics of real…
In text-driven 3D scene generation, object layout serves as a crucial intermediate representation that bridges high-level language instructions with detailed geometric output. It not only provides a structural blueprint for ensuring…
Industrial Anomaly Detection (IAD) is critical for quality control, but existing methods struggle with subtle, geometric defects. Standard 2D (RGB) images are sensitive to texture and lighting but often miss fine geometric anomalies. While…
Collecting multi-view driving scenario videos to enhance the performance of 3D visual perception tasks presents significant challenges and incurs substantial costs, making generative models for realistic data an appealing alternative. Yet,…
Most existing video diffusion models (VDMs) are limited to mere text conditions. Thereby, they are usually lacking in control over visual appearance and geometry structure of the generated videos. This work presents Moonshot, a new video…
This paper presents a new dataset for Novel View Synthesis, generated from a high-quality, animated film with stunning realism and intricate detail. Our dataset captures a variety of dynamic scenes, complete with detailed textures,…
Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset.…
Synthesizing realistic Martian landscape videos is crucial for mission rehearsal and robotic simulation. However, this task poses unique challenges due to the scarcity of high-quality Martian data and the significant domain gap between…
With the increasing use of RetrievalAugmented Generation (RAG), strong retrieval models have become more important than ever. In healthcare, multimodal retrieval models that combine information from both text and images offer major…
Recent advances in deep generative models have led to significant progress in video generation, yet the fidelity of AI-generated videos remains limited. Synthesized content often exhibits visual artifacts such as temporally inconsistent…
Music is essential when editing videos, but selecting music manually is difficult and time-consuming. Thus, we seek to automatically generate background music tracks given video input. This is a challenging task since it requires…
We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for…
Retrospective novel view synthesis (NVS) of dynamic scenes is fundamental to applications such as sports. Recent dynamic 3D Gaussian Splatting (3DGS) approaches introduce temporally coupled formulations to enforce motion coherence across…
Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static images, failing to capture the temporal complexity of…
We present GEN3C, a generative video model with precise Camera Control and temporal 3D Consistency. Prior video models already generate realistic videos, but they tend to leverage little 3D information, leading to inconsistencies, such as…
Automated retinal image medical description generation is crucial for streamlining medical diagnosis and treatment planning. Existing challenges include the reliance on learned retinal image representations, difficulties in handling…
Scaling generative inverse and forward rendering to real-world scenarios is bottlenecked by the limited realism and temporal coherence of existing synthetic datasets. To bridge this persistent domain gap, we introduce a large-scale, dynamic…
Controllable generative models for images and videos have seen significant success, yet 3D scene generation, especially in unbounded scenarios like autonomous driving, remains underdeveloped. Existing methods lack flexible controllability…
Generative models have achieved impressive fidelity in text-to-image synthesis, yet struggle with complex compositional prompts involving multiple constraints. We introduce \textbf{M3 (Multi-Modal, Multi-Agent, Multi-Round)}, a…
Current datasets for action recognition tasks face limitations stemming from traditional collection and generation methods, including the constrained range of action classes, absence of multi-viewpoint recordings, limited diversity, poor…