Adding three arXiv papers: SADG, SA4D, DynSUP

README.md

@@ -1615,6 +1615,16 @@ We present 3DGS-CD, the first 3D Gaussian Splatting (3DGS)-based method for dete
 
 [📄 Paper](https://arxiv.org/pdf/2411.03706) | [💻 Code (not yet)](https://github.com/520xyxyzq/3DGS-CD)
 
+### 15. DynSUP: Dynamic Gaussian Splatting from An Unposed Image Pair
+**Authors**: Weihang Li, Weirong Chen, Shenhan Qian, Jiajie Chen, Daniel Cremers, Haoang Li
+
+<details span>
+<summary><b>Abstract</b></summary>
+Recent advances in 3D Gaussian Splatting have shown promising results. Existing methods typically assume static scenes and/or multiple images with prior poses. Dynamics, sparse views, and unknown poses significantly increase the problem complexity due to insufficient geometric constraints. To overcome this challenge, we propose a method that can use only two images without prior poses to fit Gaussians in dynamic environments. To achieve this, we introduce two technical contributions. First, we propose an object-level two-view bundle adjustment. This strategy decomposes dynamic scenes into piece-wise rigid components, and jointly estimates the camera pose and motions of dynamic objects. Second, we design an SE(3) field-driven Gaussian training method. It enables fine-grained motion modeling through learnable per-Gaussian transformations. Our method leads to high-fidelity novel view synthesis of dynamic scenes while accurately preserving temporal consistency and object motion. Experiments on both synthetic and real-world datasets demonstrate that our method significantly outperforms state-of-the-art approaches designed for the cases of static environments, multiple images, and/or known poses. Our project page is available at https://colin-de.github.io/DynSUP/.
+</details>
+
+[📄 Paper](https://arxiv.org/abs/2412.00851) | [🌐 Project Page](https://colin-de.github.io/DynSUP/) | [💻 Code (not yet)]()
+
 ## 2023:
 ### 1. [3DV '24] Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis
 **Authors**: Jonathon Luiten, Georgios Kopanas, Bastian Leibe, Deva Ramanan
@@ -1933,6 +1943,24 @@ In this paper, we introduce a novel voting-based method that extends 2D segmenta
 </details>
 
 [📄 Paper](https://arxiv.org/abs/2409.11681) | [🌐 Project Page](https://jojijoseph.github.io/3dgs-segmentation/) | [💻 Code](https://github.com/JojiJoseph/3dgs-gradient-segmentation)
+
+### 15. Segment Any 4D Gaussians
+**Authors**: Shengxiang Ji, Guanjun Wu, Jiemin Fang, Jiazhong Cen, Taoran Yi, Wenyu Liu, Qi Tian, Xinggang Wang
+<details span>
+<summary><b>Abstract</b></summary>
+Modeling, understanding, and reconstructing the real world are crucial in XR/VR. Recently, 3D Gaussian Splatting (3D-GS) methods have shown remarkable success in modeling and understanding 3D scenes. Similarly, various 4D representations have demonstrated the ability to capture the dynamics of the 4D world. However, there is a dearth of research focusing on segmentation within 4D representations. In this paper, we propose Segment Any 4D Gaussians (SA4D), one of the first frameworks to segment anything in the 4D digital world based on 4D Gaussians. In SA4D, an efficient temporal identity feature field is introduced to handle Gaussian drifting, with the potential to learn precise identity features from noisy and sparse input. Additionally, a 4D segmentation refinement process is proposed to remove artifacts. Our SA4D achieves precise, high-quality segmentation within seconds in 4D Gaussians and shows the ability to remove, recolor, compose, and render high-quality anything masks. More demos are available at: https://jsxzs.github.io/sa4d/.
+</details>
+
+[📄 Paper](https://arxiv.org/abs/2407.04504) | [🌐 Project Page](https://jsxzs.github.io/sa4d/) | [💻 Code](https://github.com/jsxzs/SA4D)
+
+### 16. SADG: Segment Any Dynamic Gaussians Without Object Trackers
+**Authors**: Yun-Jin Li, Mariia Gladkova, Yan Xia, Daniel Cremers
+<details span>
+<summary><b>Abstract</b></summary>
+Understanding dynamic 3D scenes is fundamental for various applications, including extended reality (XR) and autonomous driving. Effectively integrating semantic information into 3D reconstruction enables holistic representation that opens opportunities for immersive and interactive applications. We introduce SADG, Segment Any Dynamic Gaussian Without Object Trackers, a novel approach that combines dynamic Gaussian Splatting representation and semantic information without reliance on object IDs. In contrast to existing works, we do not rely on supervision based on object identities to enable consistent segmentation of dynamic 3D objects. To this end, we propose to learn semantically-aware features by leveraging masks generated from the Segment Anything Model (SAM) and utilizing our novel contrastive learning objective based on hard pixel mining. The learned Gaussian features can be effectively clustered without further post-processing. This enables fast computation for further object-level editing, such as object removal, composition, and style transfer by manipulating the Gaussians in the scene. We further extend several dynamic novel-view datasets with segmentation benchmarks to enable testing of learned feature fields from unseen viewpoints. We evaluate SADG on proposed benchmarks and demonstrate the superior performance of our approach in segmenting objects within dynamic scenes along with its effectiveness for further downstream editing tasks.
+</details>
+
+[📄 Paper](https://arxiv.org/abs/2411.19290) | [🌐 Project Page](https://yunjinli.github.io/project-sadg/) | [💻 Code](https://github.com/yunjinli/SADG-SegmentAnyDynamicGaussian)
 
 ## 2023:
 ### 1. [CVPR '24] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting