中文
相关论文

相关论文: RealisticDreamer: Guidance Score Distillation for …

200 篇论文

3D Gaussian Splatting (3DGS) has exhibited remarkable efficacy in novel view synthesis (NVS). However, it suffers from a significant drawback: achieving high-fidelity rendering typically necessitates a large number of 3D Gaussians,…

计算机视觉与模式识别 · 计算机科学 2025-08-20 Lintao Xiang , Xinkai Chen , Jianhuang Lai , Guangcong Wang

Score Distillation Sampling (SDS) leverages pretrained 2D diffusion models to advance text-to-3D generation but neglects multi-view correlations, being prone to geometric inconsistencies and multi-face artifacts in the generated 3D content.…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Feng Yang , Wenliang Qian , Wangmeng Zuo , Hui Li

Score distillation sampling (SDS), the methodology in which the score from pretrained 2D diffusion models is distilled into 3D representation, has recently brought significant advancements in text-to-3D generation task. However, this…

计算机视觉与模式识别 · 计算机科学 2024-07-02 Min-Seop Kwak , Donghoon Ahn , Ines Hyeonsu Kim , Jin-Hwa Kim , Seungryong Kim

3D Gaussian Splatting (3DGS) has achieved excellent rendering quality with fast training and rendering speed. However, its optimization process lacks explicit geometric constraints, leading to suboptimal geometric reconstruction in regions…

计算机视觉与模式识别 · 计算机科学 2025-02-12 Lin-Zhuo Chen , Kangjie Liu , Youtian Lin , Siyu Zhu , Zhihao Li , Xun Cao , Yao Yao

3D Gaussian Splatting has recently enabled fast and photorealistic reconstruction of static 3D scenes. However, dynamic editing of such scenes remains a significant challenge. We introduce a novel framework, Physics-Guided Score…

图形学 · 计算机科学 2026-03-26 Gal Fiebelman , Hadar Averbuch-Elor , Sagie Benaim

The success of 3DGS in generative and editing applications has sparked growing interest in 3DGS-based style transfer. However, current methods still face two major challenges: (1) multi-view inconsistency often leads to style conflicts,…

计算机视觉与模式识别 · 计算机科学 2025-12-04 Yitong Yang , Yinglin Wang , Changshuo Wang , Huajie Wang , Shuting He

While 2D diffusion models generate realistic, high-detail images, 3D shape generation methods like Score Distillation Sampling (SDS) built on these 2D diffusion models produce cartoon-like, over-smoothed shapes. To help explain this…

We propose a method to enhance 3D Gaussian Splatting (3DGS)~\cite{Kerbl2023}, addressing challenges in initialization, optimization, and density control. Gaussian Splatting is an alternative for rendering realistic images while supporting…

计算机视觉与模式识别 · 计算机科学 2025-07-02 Xingjun Wang , Lianlei Shan

Recent advancements in 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have achieved impressive results in real-time 3D reconstruction and novel view synthesis. However, these methods struggle in large-scale, unconstrained…

计算机视觉与模式识别 · 计算机科学 2025-04-03 Niluthpol Chowdhury Mithun , Tuan Pham , Qiao Wang , Ben Southall , Kshitij Minhas , Bogdan Matei , Stephan Mandt , Supun Samarasekera , Rakesh Kumar

Score distillation of 2D diffusion models has proven to be a powerful mechanism to guide 3D optimization, for example enabling text-based 3D generation or single-view reconstruction. A common limitation of existing score distillation…

计算机视觉与模式识别 · 计算机科学 2025-04-17 Yanbo Xu , Jayanth Srinivasa , Gaowen Liu , Shubham Tulsiani

Image-based 3D generation has vast applications in robotics and gaming, where high-quality, diverse outputs and consistent 3D representations are crucial. However, existing methods have limitations: 3D diffusion models are limited by…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Ye Tao , Jiawei Zhang , Yahao Shi , Dongqing Zou , Bin Zhou

Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style video distillation faces two coupled challenges: the fake score must track a continuously…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Zhuguanyu Wu , Ruihao Gong , Yang Yong , Yushi Huang , Xiangyu Fan , Lei Yang , Dahua Lin , Xianglong Liu

Recently, 3D Gaussian Splatting (3DGS) has demonstrated remarkable success in 3D reconstruction and novel view synthesis. However, reconstructing 3D scenes from sparse viewpoints remains highly challenging due to insufficient visual…

计算机视觉与模式识别 · 计算机科学 2025-09-24 Zhaorui Wang , Yi Gu , Deming Zhou , Renjing Xu

We present GSD, a diffusion model approach based on Gaussian Splatting (GS) representation for 3D object reconstruction from a single view. Prior works suffer from inconsistent 3D geometry or mediocre rendering quality due to improper…

计算机视觉与模式识别 · 计算机科学 2024-10-30 Yuxuan Mu , Xinxin Zuo , Chuan Guo , Yilin Wang , Juwei Lu , Xiaofeng Wu , Songcen Xu , Peng Dai , Youliang Yan , Li Cheng

3D Gaussian Splatting (3DGS) achieves remarkable results in the field of surface reconstruction. However, when Gaussian normal vectors are aligned within the single-view projection plane, while the geometry appears reasonable in the current…

计算机视觉与模式识别 · 计算机科学 2025-08-14 Bo Jia , Yanan Guo , Ying Chang , Benkui Zhang , Ying Xie , Kangning Du , Lin Cao

Novel view synthesis under sparse views has been a long-term important challenge in 3D reconstruction. Existing works mainly rely on introducing external semantic or depth priors to supervise the optimization of 3D representations. However,…

计算机视觉与模式识别 · 计算机科学 2024-12-04 Qisen Wang , Yifan Zhao , Jiawei Ma , Jia Li

Score Distillation Sampling (SDS) has made significant strides in distilling image-generative models for 3D generation. However, its maximum-likelihood-seeking behavior often leads to degraded visual quality and diversity, limiting its…

计算机视觉与模式识别 · 计算机科学 2025-01-10 Runjie Yan , Yinbo Chen , Xiaolong Wang

Recent advancements in 3D editing have highlighted the potential of text-driven methods in real-time, user-friendly AR/VR applications. However, current methods rely on 2D diffusion models without adequately considering multi-view…

计算机视觉与模式识别 · 计算机科学 2025-04-21 Dong In Lee , Hyeongcheol Park , Jiyoung Seo , Eunbyung Park , Hyunje Park , Ha Dam Baek , Sangheon Shin , Sangmin Kim , Sangpil Kim

Existing Score Distillation Sampling (SDS)-based methods have driven significant progress in text-to-3D generation. However, 3D models produced by SDS-based methods tend to exhibit over-smoothing and low-quality outputs. These issues arise…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Uy Dieu Tran , Minh Luu , Phong Ha Nguyen , Khoi Nguyen , Binh-Son Hua

Although recent advancements in text-to-3D generation have significantly improved generation quality, issues like limited level of detail and low fidelity still persist, which requires further improvement. To understand the essence of those…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Zongrui Li , Minghui Hu , Qian Zheng , Xudong Jiang
‹ 上一页 1 2 3 10 下一页 ›