Physically Aware 360$^\circ$ View Generation from a Single Image using Disentangled Scene Embeddings
By: Karthikeya KV, Narendra Bandaru
Potential Business Impact:
Creates realistic 3D views from one picture.
We introduce Disentangled360, an innovative 3D-aware technology that integrates the advantages of direction disentangled volume rendering with single-image 360° unique view synthesis for applications in medical imaging and natural scene reconstruction. In contrast to current techniques that either oversimplify anisotropic light behavior or lack generalizability across various contexts, our framework distinctly differentiates between isotropic and anisotropic contributions inside a Gaussian Splatting backbone. We implement a dual-branch conditioning framework, one optimized for CT intensity driven scattering in volumetric data and the other for real-world RGB scenes through normalized camera embeddings. To address scale ambiguity and maintain structural realism, we present a hybrid pose agnostic anchoring method that adaptively samples scene depth and material transitions, functioning as stable pivots during scene distillation. Our design integrates preoperative radiography simulation and consumer-grade 360° rendering into a singular inference pipeline, facilitating rapid, photorealistic view synthesis with inherent directionality. Evaluations on the Mip-NeRF 360, RealEstate10K, and DeepDRR datasets indicate superior SSIM and LPIPS performance, while runtime assessments confirm its viability for interactive applications. Disentangled360 facilitates mixed-reality medical supervision, robotic perception, and immersive content creation, eliminating the necessity for scene-specific finetuning or expensive photon simulations.
Similar Papers
Seam360GS: Seamless 360° Gaussian Splatting from Real-World Omnidirectional Images
CV and Pattern Recognition
Fixes blurry 360-degree pictures for VR.
GEN3D: Generating Domain-Free 3D Scenes from a Single Image
CV and Pattern Recognition
Creates realistic 3D worlds from one picture.
DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training
CV and Pattern Recognition
Makes 360 pictures look real and smooth.