# GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views

arXiv: https://arxiv.org/abs/2411.11363 · HTML: https://mlsanity.com/paper/2411.11363/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 71 of its 96 references that are in the map.
- First posted on arXiv 18 Nov 2024.

## Builds on (most cited first, 30 of 71)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [HexPlane: A Fast Representation for Dynamic Scenes](https://mlsanity.com/paper/2301.09632/) (2023)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [Splatter Image: Ultra-Fast Single-View 3D Reconstruction](https://mlsanity.com/paper/2312.13150/) (2023)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [Fast Dynamic Radiance Fields with Time-Aware Neural Voxels](https://mlsanity.com/paper/2205.15285/) (2022)
- [Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2312.16812/) (2023)
- [Neural Point-Based Graphics](https://mlsanity.com/paper/1906.08240/) (2019)

## Built on by (most cited first, 22 of 22)

- [HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers](https://mlsanity.com/paper/2506.03118/) (2025)
- [TinySplat: Feedforward Approach for Generating Compact 3D Scene Representation](https://mlsanity.com/paper/2506.09479/) (2025)
- [WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction](https://mlsanity.com/paper/2502.01045/) (2025)
- [ProSplat: Improved Feed-Forward 3D Gaussian Splatting for Wide-Baseline Sparse Views](https://mlsanity.com/paper/2506.07670/) (2025)
- [R3-Avatar: Record and Retrieve Temporal Codebook for Reconstructing Photorealistic Human Avatars](https://mlsanity.com/paper/2503.12751/) (2025)
- [Micro-macro Gaussian Splatting with Enhanced Scalability for Unconstrained Scene Reconstruction](https://mlsanity.com/paper/2506.13516/) (2025)
- [HART: Human Aligned Reconstruction Transformer](https://mlsanity.com/paper/2509.26621/) (2025)
- [Splat-SAP: Feed-Forward Gaussian Splatting for Human-Centered Scene with Scale-Aware Point Map Reconstruction](https://mlsanity.com/paper/2511.22704/) (2025)
- [Real-Time Human Frontal View Synthesis from a Single Image](https://mlsanity.com/paper/2603.15433/) (2026)
- [SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis](https://mlsanity.com/paper/2605.07287/) (2026)
- [SPARE-GS: Structural Parsimony and Resource Efficiency for 3D Gaussian Splatting](https://mlsanity.com/paper/2607.16624/) (2026)
- [Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGS](https://mlsanity.com/paper/2510.17479/) (2025)
- [Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation](https://mlsanity.com/paper/2605.21258/) (2026)
- [HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation](https://mlsanity.com/paper/2511.00468/) (2025)
- [CUS-GS: A Compact Unified Structured Gaussian Splatting Framework for Multimodal Scene Representation](https://mlsanity.com/paper/2511.17904/) (2025)
- [GVSynergy-Det: Synergistic Gaussian-Voxel Representations for Multi-View 3D Object Detection](https://mlsanity.com/paper/2512.23176/) (2025)
- [3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis](https://mlsanity.com/paper/2604.11211/) (2026)
- [DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis](https://mlsanity.com/paper/2604.13416/) (2026)
- [DSD-GS: Dynamic-Static Decomposition of Gaussian Splatting for Efficient and High-Fidelity Dynamic Scene Reconstruction](https://mlsanity.com/paper/2605.30863/) (2026)
- [GS-NFS: Bandwidth-adaptive Streaming of Dynamic Gaussian Splats and Point Clouds](https://mlsanity.com/paper/2606.05650/) (2026)
- [IBRSteG: Learning a Generalizable Steganography Framework for 3D Gaussian Splatting](https://mlsanity.com/paper/2606.30024/) (2026)
- [Tele360: Real-Time Feed-Forward Human Reconstruction from Sparse Unposed Cameras](https://mlsanity.com/paper/2609.15032/) (2026)

## Abstract (arXiv)

Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject optimization which does not meet the requirement of real-time rendering in an interactive application. We propose a generalizable Gaussian Splatting approach for high-resolution image rendering under a sparse-view camera setting. To this end, we introduce Gaussian parameter maps defined on the source views and directly regress Gaussian properties for instant novel view synthesis without any fine-tuning or optimization. We train our Gaussian parameter regression module on human-only data or human-scene data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. The proposed framework is fully differentiable with both depth and rendering supervision or with only rendering supervision. We further introduce a regularization term and an epipolar attention mechanism to preserve geometry consistency between two source views, especially when neglecting depth supervision. Experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed.