Related papers: PrevizWhiz: Combining Rough 3D Scenes and 2D Video…
To solve the issue of video dehazing, there are two main tasks to attain: how to align adjacent frames to the reference frame; how to restore the reference frame. Some papers adopt explicit approaches (e.g., the Markov random field, optical…
Video-to-video synthesis (vid2vid) aims for converting high-level semantic inputs to photorealistic videos. While existing vid2vid methods can achieve short-term temporal consistency, they fail to ensure the long-term one. This is because…
Open-vocabulary 3D scene graph generation seeks to describe object instances and their relations with flexible natural-language predicates. The central difficulty is not only vocabulary expansion, but supervision reliability: relation…
Pairwise pose estimation from images with little or no overlap is an open challenge in computer vision. Existing methods, even those trained on large-scale datasets, struggle in these scenarios due to the lack of identifiable…
3D open-vocabulary scene graph methods are a promising map representation for embodied agents, however many current approaches are computationally expensive. In this paper, we reexamine the critical design choices established in previous…
3D scene generation is a core technology for gaming, film/VFX, and VR/AR. Growing demand for rapid iteration, high-fidelity detail, and accessible content creation has further increased interest in this area. Existing methods broadly follow…
We introduce the concept of a subjective camera to reconstruct meaningful moments that physical cameras fail to capture. We propose Subjective Camera 1.0, a framework for reconstructing real-world scenes from readily accessible subjective…
Recent advancements in diffusion models have revolutionized video generation, enabling the creation of high-quality, temporally consistent videos. However, generating high frame-rate (FPS) videos remains a significant challenge due to…
Eliminating time-consuming post-production processes and delivering high-quality videos in today's fast-paced digital landscape are the key advantages of real-time approaches. To address these needs, we present Real Time GAZED: a real-time…
Existing multi-view 3D object reconstruction methods heavily rely on sufficient overlap between input views, where occlusions and sparse coverage in practice frequently yield severe reconstruction incompleteness. Recent advancements in…
With the rapid development of generative technology, current generative models can generate high-fidelity digital content and edit it in a controlled manner. However, there is a risk that malicious individuals might misuse these…
Humans possess a remarkable ability to mentally explore and replay 3D environments they have previously experienced. Inspired by this mental process, we present EvoWorld: a world model that bridges panoramic video generation with evolving…
Video generation has achieved rapid progress benefiting from high-quality renderings provided by powerful image generators. We regard the video synthesis task as generating a sequence of images sharing the same contents but varying in…
Image dehazing is one of the important and popular topics in computer vision and machine learning. A reliable real-time dehazing method with reliable performance is highly desired for many applications such as autonomous driving, security…
AI video generation has lowered barriers to video creation, but current tools still struggle with inconsistency. Filmmakers often find that clips fail to match characters and backgrounds, making it difficult to build coherent sequences. A…
Generating flexible-view 3D scenes, including 360{\deg} rotation and zooming, from single images is challenging due to a lack of 3D data. To this end, we introduce FlexWorld, a novel framework consisting of two key components: (1) a strong…
Creating 3D character animations traditionally requires significant time and effort from the animator. Advancements in generative methods now enable easy creation of multiple character animation variations for use or further editing.…
Significant progress has been made in text-to-video generation through the use of powerful generative models and large-scale internet data. However, substantial challenges remain in precisely controlling individual concepts within the…
Large-scale video generative models are trained on vast and diverse visual data, enabling them to internalize rich structural, semantic, and dynamic priors of the visual world. While these models have demonstrated impressive generative…
While large-scale datasets have driven significant progress in Text-to-Video (T2V) generative models, these models remain highly sensitive to input prompts, demonstrating that prompt design is critical to generation quality. Current methods…