Gaussian Mapping for Evolving Scenes

The paper presents SymGS, a novel framework for compressing 3D Gaussian Splatting data by leveraging local symmetries. This approach aims to reduce the memory footprint associated with complex scenes, which can reach several gigabytes. By introducing learnable mirrors to eliminate redundant primitives, SymGS enhances existing compression methods, achieving significant improvements in efficiency compared to traditional techniques.

The paper presents a novel approach to 3D Gaussian super-resolution, addressing the limitations of existing methods that operate at fixed scale factors. The proposed framework integrates scale-aware rendering, generative prior-guided optimization, and progressive super-resolving, allowing for high-resolution rendering of arbitrary scale factors using a single 3D model. Experimental results indicate a significant improvement in rendering quality, achieving a PSNR gain of 6.59 dB over traditional methods.

RoboTidy is a new benchmark designed for language-guided household tidying, addressing the limitations of current benchmarks that fail to model user preferences and support mobility. It features 500 photorealistic 3D Gaussian Splatting household scenes and provides extensive manipulation and navigation trajectories to facilitate training and evaluation in Vision-Language-Action and Vision-Language-Navigation tasks.

Gaussian See, Gaussian Do is a new method for semantic 3D motion transfer from multiview video. This approach allows for rig-free, cross-category motion transfer between objects that have semantically meaningful correspondence. By utilizing implicit motion transfer techniques, the method extracts motion embeddings from source videos and applies them to static target shapes, resulting in improved motion fidelity and structural consistency in 3D Gaussian Splatting reconstruction.

The introduction of 3D Gaussian Splatting (3DGS) has advanced novel view synthesis, but existing methods still face visual discrepancies at unseen sampling rates. These include blurring artifacts when zooming in and staircase artifacts when zooming out, attributed to limitations in alpha blending. A new approach, Gaussian Blending, is proposed to treat alpha and transmittance as spatially varying distributions, potentially improving rendering quality.

Wave-Former is a new method for high-accuracy 3D shape reconstruction of completely occluded everyday objects, utilizing millimeter-wave (mmWave) wireless signals. This innovative approach can penetrate common obstructions and reflect off hidden objects, overcoming limitations of previous methods that faced noise and coverage issues. The technology has potential applications in robotics, augmented reality, and logistics.

The paper presents a novel physical adversarial attack targeting stereo matching models used in autonomous driving. Unlike traditional attacks that utilize 2D patches, this approach employs a 3D physical adversarial example (PAE) with global camouflage texture, enhancing visual consistency across various viewpoints. Additionally, a new 3D stereo matching rendering module is introduced to align the PAE with real-world positions in binocular vision, addressing the disparity effects of stereo cameras.

The Geometry-guided Multi-View Diffusion Model (GeoMVD) has been proposed to enhance multi-view image generation, addressing challenges in maintaining cross-view consistency and producing high-resolution outputs. By utilizing geometric information extraction techniques, including depth maps and segmentation masks, GeoMVD aims to create images that are both consistent across views and rich in detail, making it valuable for applications in 3D reconstruction, virtual reality, and augmented reality.