컨퍼런스 썸네일형 리스트형 [(Don't) Make Some Noise: Denoising] Neural Kernel Regression for Consistent Monte Carlo Denoising https://dl.acm.org/doi/10.1145/3687949 Neural Kernel Regression for Consistent Monte Carlo Denoising | ACM Transactions on GraphicsUnbiased Monte Carlo path tracing that is extensively used in realistic rendering produces undesirable noise, especially with low samples per pixel (spp). Recently, several methods have coped with this problem by importing unbiased noisy images and ...dl.acm.org Neur.. 더보기 [(Don't) Make Some Noise: Denoising] Spatiotemporal Bilateral Gradient Filtering for Inverse Rendering https://weschang.com/publications/stadam/ Spatiotemporal Bilateral Gradient Filtering for Inverse RenderingWe introduce a spatiotemporal optimizer for inverse rendering which combines the temporal filtering of Adam with spatial cross-bilateral filtering to enable higher quality reconstructions in texture, volume, and geometry recovery.weschang.comSpatiotemporal Bilateral Gradient Filtering for I.. 더보기 [(Don't) Make Some Noise: Denoising] Filtering-Based Reconstruction for Gradient-Domain Rendering https://dl.acm.org/doi/10.1145/3680528.3687568 Filtering-Based Reconstruction for Gradient-Domain Rendering | SIGGRAPH Asia 2024 Conference PapersPublication History Published: 03 December 2024dl.acm.org Filtering-Based Reconstruction for Gradient-Domain RenderingMonte Carlo 렌더링은 사실적인 이미지를 생성하는 데 사용되지만, 노이즈 문제로 인해 고품질 재구성이 어렵습니다. 이번 SIGGRAPH Asia 2024에서 발표된 "Filtering-Based Reconstruction for Gr.. 더보기 [(Don't) Make Some Noise: Denoising] Online Neural Denoising with Cross-Regression for Interactive Rendering https://dl.acm.org/doi/10.1145/3687938 Online Neural Denoising with Cross-Regression for Interactive Rendering | ACM Transactions on GraphicsGenerating a rendered image sequence through Monte Carlo ray tracing is an appealing option when one aims to accurately simulate various lighting effects. Unfortunately, interactive rendering scenarios limit the allowable sample size for such sampling-...dl.. 더보기 [(Don't) Make Some Noise: Denoising] A Statistical Approach to Monte Carlo Denoising https://dl.acm.org/doi/10.1145/3680528.3687591 A Statistical Approach to Monte Carlo Denoising | SIGGRAPH Asia 2024 Conference PapersPublication History Published: 03 December 2024dl.acm.org A Statistical Approach to Monte Carlo Denoising: 기존 방법의 세련된 개선Monte Carlo 기반 렌더링에서 발생하는 노이즈 문제는 오래된 과제입니다. 이번 SIGGRAPH Asia 2024에서 발표된 "A Statistical Approach to Monte Carlo Denoising" 논문은 딥러닝 대신 통계적 필터링을 활용.. 더보기 ASIA SIGGRAP DAY 2 보호되어 있는 글입니다. 더보기 [Text, Texturing, and Stylization] Camera Settings as Tokens: Modeling Photography on Latent Diffusion Models https://dl.acm.org/doi/10.1145/3680528.3687635 Camera Settings as Tokens: Modeling Photography on Latent Diffusion Models | SIGGRAPH Asia 2024 Conference PapersPublication History Published: 03 December 2024dl.acm.org Camera Settings as Tokens: AI와 사진의 새로운 융합텍스트-투-이미지 생성 모델은 예술적 창작에서 혁신을 가져왔지만, 실제 사진 촬영의 물리적 요소를 반영하는 데는 한계가 있었습니다. "Camera Settings as Tokens"는 이러한 문제를 해결하기 위해 카메라 설정(초점 거리, 조리개 값,.. 더보기 [Text, Texturing, and Stylization] Compositional Neural Textures https://dl.acm.org/doi/10.1145/3680528.3687561 Compositional Neural Textures | SIGGRAPH Asia 2024 Conference PapersPublication History Published: 03 December 2024dl.acm.org Compositional Neural Textures: 텍스처 편집을 위한 새로운 접근Compositional Neural Textures는 텍스처를 더 효율적으로 생성, 편집할 수 있도록 설계된 완전히 새로운 방식의 신경망 기반 텍스처 모델입니다. 이 논문은 텍스처를 "Neural Textons"라는 개념으로 분해하여 표현하며, 각 텍스처 요소를 2D Gaussian 함수로 나타냅니다. 이를 통해 .. 더보기 이전 1 2 3 4 5 6 7 ··· 9 다음
