From f9d0af29b896675675fb510a6d1223b7fd5b8c07 Mon Sep 17 00:00:00 2001 From: paulbzm Date: Wed, 24 Jul 2024 14:07:29 +0200 Subject: [PATCH] improve summary --- methods/wang2024end.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/methods/wang2024end.md b/methods/wang2024end.md index 7896127..8693e0a 100644 --- a/methods/wang2024end.md +++ b/methods/wang2024end.md @@ -1,3 +1,3 @@ ### End-to-End Rate-Distortion Optimized 3D Gaussian Representation -This paper introduces RDO-Gaussian, an end-to-end Rate-Distortion Optimized 3D Gaussian representation. The authors achieve flexible, continuous rate control by formulating 3D Gaussian representation learning as a joint optimization of rate and distortion. Rate-distortion optimization is realized through dynamic pruning and entropy-constrained vector quantization (ECVQ), optimizing rate and distortion simultaneously. Gaussian pruning involves learning a mask to eliminate redundant Gaussians and adaptive SHs pruning assigns varying SH degrees to each Gaussian based on material and illumination needs. The covariance and color attributes are discretized through ECVQ, which performs vector quantization. \ No newline at end of file +This paper introduces RDO-Gaussian, an end-to-end Rate-Distortion Optimized 3D Gaussian representation. The authors achieve flexible, continuous rate control by formulating 3D Gaussian representation learning as a joint optimization of rate and distortion. Rate-distortion optimization is realized through dynamic pruning and entropy-constrained vector quantization (ECVQ). Gaussian pruning involves learning a mask to eliminate redundant Gaussians and adaptive SHs pruning assigns varying SH degrees to each Gaussian based on material and illumination needs. The covariance and color attributes are discretized through ECVQ, which performs vector quantization. \ No newline at end of file