中文
相关论文

相关论文: PixelSynth: Generating a 3D-Consistent Experience …

200 篇论文

Synthesizing extrapolated views remains a difficult task, especially in urban driving scenes, where the only reliable sources of data are limited RGB captures and sparse LiDAR points. To address this problem, we present PointmapDiff, a…

Zero-shot novel view synthesis (NVS) from a single image is an essential problem in 3D object understanding. While recent approaches that leverage pre-trained generative models can synthesize high-quality novel views from in-the-wild…

计算机视觉与模式识别 · 计算机科学 2024-03-18 Jianglong Ye , Peng Wang , Kejie Li , Yichun Shi , Heng Wang

Humans can infer 3D structure from 2D images of an object based on past experience and improve their 3D understanding as they see more images. Inspired by this behavior, we introduce SAP3D, a system for 3D reconstruction and novel view…

计算机视觉与模式识别 · 计算机科学 2024-04-05 Xinyang Han , Zelin Gao , Angjoo Kanazawa , Shubham Goel , Yossi Gandelsman

The synthesis of immersive 3D scenes from text is rapidly maturing, driven by novel video generative models and feed-forward 3D reconstruction, with vast potential in AR/VR and world modeling. While panoramic images have proven effective…

计算机视觉与模式识别 · 计算机科学 2026-05-04 Felix Wimbauer , Fabian Manhardt , Michael Oechsle , Nikolai Kalischek , Christian Rupprecht , Daniel Cremers , Federico Tombari

While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in maintaining multi-view consistency. Classical approaches…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Yufeng Chi , Huimin Ma , Kafeng Wang , Jianmin Li

Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, existing models typically lack a 3D representation of the environment, meaning 3D consistency must…

计算机视觉与模式识别 · 计算机科学 2026-03-05 Samuel Garcin , Thomas Walker , Steven McDonagh , Tim Pearce , Hakan Bilen , Tianyu He , Kaixin Wang , Jiang Bian

We present a new approach for synthesizing novel views of people in new poses. Our novel differentiable renderer enables the synthesis of highly realistic images from any viewpoint. Rather than operating over mesh-based structures, our…

计算机视觉与模式识别 · 计算机科学 2023-03-29 Guillaume Rochette , Chris Russell , Richard Bowden

The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Chenhan Jiang , Yu Chen , Qingwen Zhang , Jifei Song , Songcen Xu , Dit-Yan Yeung , Jiankang Deng

A concept of light-fields computed from multiple view images on regular grids has proven its benefit for scene representations, and supported realistic renderings of novel views and photographic effects such as refocusing and shallow depth…

计算机视觉与模式识别 · 计算机科学 2025-10-24 Hyunjun Jung , Hae-Gon Jeon

We present GeoSynth, a model for synthesizing satellite images with global style and image-driven layout control. The global style control is via textual prompts or geographic location. These enable the specification of scene semantics or…

计算机视觉与模式识别 · 计算机科学 2024-04-11 Srikumar Sastry , Subash Khanal , Aayush Dhakal , Nathan Jacobs

We introduce the task of mixed-view panorama synthesis, where the goal is to synthesize a novel panorama given a small set of input panoramas and a satellite image of the area. This contrasts with previous work which only uses input…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Zhexiao Xiong , Xin Xing , Scott Workman , Subash Khanal , Nathan Jacobs

Dynamic novel view synthesis aims to capture the temporal evolution of visual content within videos. Existing methods struggle to distinguishing between motion and structure, particularly in scenarios where camera poses are either unknown…

计算机视觉与模式识别 · 计算机科学 2024-01-12 Chaoyang Wang , Peiye Zhuang , Aliaksandr Siarohin , Junli Cao , Guocheng Qian , Hsin-Ying Lee , Sergey Tulyakov

World building with 3D scene representations is increasingly important for content creation, simulation, and interactive experiences, yet real workflows are inherently iterative: creators must repeatedly extend an existing scene under user…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Zijian He , Renjie Liu , Yihao Wang , Weizhi Zhong , Huan Yuan , Kun Gai , Guangrun Wang , Guanbin Li

Scene depth estimation from stereo and monocular imagery is critical for extracting 3D information for downstream tasks such as scene understanding. Recently, learning-based methods for depth estimation have received much attention due to…

计算机视觉与模式识别 · 计算机科学 2021-10-12 Zhaoshuo Li , Nathan Drenkow , Hao Ding , Andy S. Ding , Alexander Lu , Francis X. Creighton , Russell H. Taylor , Mathias Unberath

Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images. Yet, the independent process of image generation in these prevailing methods leads to challenges in…

计算机视觉与模式识别 · 计算机科学 2024-03-01 Xianghui Yang , Yan Zuo , Sameera Ramasinghe , Loris Bazzani , Gil Avraham , Anton van den Hengel

Recent one image to 3D generation methods commonly adopt Score Distillation Sampling (SDS). Despite the impressive results, there are multiple deficiencies including multi-view inconsistency, over-saturated and over-smoothed textures, as…

计算机视觉与模式识别 · 计算机科学 2023-12-29 Junwu Zhang , Zhenyu Tang , Yatian Pang , Xinhua Cheng , Peng Jin , Yida Wei , Munan Ning , Li Yuan

The increasing demand for augmented and virtual reality applications has highlighted the importance of crafting immersive 3D scenes from a simple single-view image. However, due to the partial priors provided by single-view input, existing…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Tianyi Gong , Boyan Li , Yifei Zhong , Fangxin Wang

Novel view synthesis has shown rapid progress recently, with methods capable of producing increasingly photorealistic results. 3D Gaussian Splatting has emerged as a promising method, producing high-quality renderings of scenes and enabling…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Richard Shaw , Michal Nazarczuk , Jifei Song , Arthur Moreau , Sibi Catley-Chandar , Helisa Dhamo , Eduardo Perez-Pellitero

We present Extreme View Synthesis, a solution for novel view extrapolation that works even when the number of input images is small--as few as two. In this context, occlusions and depth uncertainty are two of the most pressing issues, and…

计算机视觉与模式识别 · 计算机科学 2019-09-02 Inchang Choi , Orazio Gallo , Alejandro Troccoli , Min H. Kim , Jan Kautz

In recent years, diffusion models have emerged as the most powerful approach in image synthesis. However, applying these models directly to video synthesis presents challenges, as it often leads to noticeable flickering contents. Although…

计算机视觉与模式识别 · 计算机科学 2023-08-11 Zhongjie Duan , Lizhou You , Chengyu Wang , Cen Chen , Ziheng Wu , Weining Qian , Jun Huang