中文
相关论文

相关论文: V-RGBX: Video Editing with Accurate Controls over …

200 篇论文

The three areas of realistic forward rendering, per-pixel inverse rendering, and generative image synthesis may seem like separate and unrelated sub-fields of graphics and vision. However, recent work has demonstrated improved estimation of…

计算机视觉与模式识别 · 计算机科学 2024-05-02 Zheng Zeng , Valentin Deschaintre , Iliyan Georgiev , Yannick Hold-Geoffroy , Yiwei Hu , Fujun Luan , Ling-Qi Yan , Miloš Hašan

We introduce IntrinsiX, a novel method that generates high-quality intrinsic images from text description. In contrast to existing text-to-image models whose outputs contain baked-in scene lighting, our approach predicts physically-based…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Peter Kocsis , Lukas Höllein , Matthias Nießner

We present X2Video, the first diffusion model for rendering photorealistic videos guided by intrinsic channels including albedo, normal, roughness, metallicity, and irradiance, while supporting intuitive multi-modal controls with reference…

图形学 · 计算机科学 2025-10-10 Zhitong Huang , Mohan Zhang , Renhan Wang , Rui Tang , Hao Zhu , Jing Liao

Generative diffusion models have advanced image editing with high-quality results and intuitive interfaces such as prompts and semantic drawing. However, these interfaces lack precise control, and the associated methods typically specialize…

The ability to edit materials of objects in images is desirable by many content creators. However, this is an extremely challenging task as it requires to disentangle intrinsic physical properties of an image. We propose an end-to-end…

计算机视觉与模式识别 · 计算机科学 2017-08-10 Guilin Liu , Duygu Ceylan , Ersin Yumer , Jimei Yang , Jyh-Ming Lien

Modern visual effects (VFX) software has made it possible for skilled artists to create imagery of virtually anything. However, the creation process remains laborious, complex, and largely inaccessible to everyday users. In this work, we…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Hao-Yu Hsu , Zhi-Hao Lin , Albert Zhai , Hongchi Xia , Shenlong Wang

We present IntrinsicWeather, a diffusion-based framework for controllable weather editing in intrinsic space. Our framework includes two components based on diffusion priors: an inverse renderer that estimates material properties, scene…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Yixin Zhu , Zuo-Liang Zhu , Jian Yang , Miloš Hašan , Jin Xie , Beibei Wang

Intrinsic image decomposition aims to separate images into physical components such as albedo, depth, normals, and illumination. While recent diffusion- and transformer-based models benefit from paired supervision from synthetic datasets,…

计算机视觉与模式识别 · 计算机科学 2025-12-05 Alara Dirik , Tuanfeng Wang , Duygu Ceylan , Stefanos Zafeiriou , Anna Frühstück

This paper offers a comprehensive analysis of recent advancements in video inpainting techniques, a critical subset of computer vision and artificial intelligence. As a process that restores or fills in missing or corrupted portions of…

计算机视觉与模式识别 · 计算机科学 2024-02-01 Shreyank N Gowda , Yash Thakre , Shashank Narayana Gowda , Xiaobo Jin

Multi-view inverse rendering aims to recover geometry, materials, and illumination consistently across multiple viewpoints. When applied to multi-view images, existing single-view approaches often ignore cross-view relationships, leading to…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Xiangzuo Wu , Chengwei Ren , Jun Zhou , Xiu Li , Yuan Liu

Estimating albedo (a.k.a., intrinsic image decomposition) from single RGB images captured in real-world environments (e.g., the MVImgNet dataset) presents a significant challenge due to the absence of paired images and their ground truth…

图形学 · 计算机科学 2025-09-03 Xiaokang Wei , Zizheng Yan , Zhangyang Xiong , Yiming Hao , Yipeng Qin , Xiaoguang Han

Video editing increasingly demands the ability to incorporate specific real-world instances into existing footage, yet current approaches fundamentally fail to capture the unique visual characteristics of particular subjects and ensure…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Shaobin Zhuang , Zhipeng Huang , Binxin Yang , Ying Zhang , Fangyikang Wang , Canmiao Fu , Chong Sun , Zheng-Jun Zha , Chen Li , Yali Wang

Recent advancements in neural rendering have excelled at novel view synthesis from multi-view RGB images. However, they often lack the capability to edit the shading or colour of the scene at a detailed point-level, while ensuring…

计算机视觉与模式识别 · 计算机科学 2024-07-02 Alireza Moazeni , Shichong Peng , Ke Li

We introduce a framework that enables both multi-view character consistency and 3D camera control in video diffusion models through a novel customization data pipeline. We train the character consistency component with recorded volumetric…

We present LumiX, a structured diffusion framework for coherent text-to-intrinsic generation. Conditioned on text prompts, LumiX jointly generates a comprehensive set of intrinsic maps (e.g., albedo, irradiance, normal, depth, and final…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Xu Han , Biao Zhang , Xiangjun Tang , Xianzhi Li , Peter Wonka

We present PRISM, a unified framework that enables multiple image generation and editing tasks in a single foundational model. Starting from a pre-trained text-to-image diffusion model, PRISM proposes an effective fine-tuning strategy to…

图形学 · 计算机科学 2025-05-15 Alara Dirik , Tuanfeng Wang , Duygu Ceylan , Stefanos Zafeiriou , Anna Frühstück

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 traditional Physically Based Rendering (PBR) offers high…

图形学 · 计算机科学 2025-04-25 Yu Guo , Zhiqiang Lao , Xiyun Song , Yubin Zhou , Zongfang Lin , Heather Yu

We present a neural rendering framework that maps a voxelized scene into a high quality image. Highly-textured objects and scene element interactions are realistically rendered by our method, despite having a rough representation as an…

计算机视觉与模式识别 · 计算机科学 2020-04-07 Konstantinos Rematas , Vittorio Ferrari

This paper introduces V$^2$Edit, a novel training-free framework for instruction-guided video and 3D scene editing. Addressing the critical challenge of balancing original content preservation with editing task fulfillment, our approach…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Yanming Zhang , Jun-Kun Chen , Jipeng Lyu , Yu-Xiong Wang

From a single picture of a scene, people can typically grasp the spatial layout immediately and even make good guesses at materials properties and where light is coming from to illuminate the scene. For example, we can reliably tell which…

计算机视觉与模式识别 · 计算机科学 2020-01-07 Kevin Karsch
‹ 上一页 1 2 3 10 下一页 ›