More Like this

1. HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork

   Bipasha Sen*, Gaurav Singh* (December 2023, Conference on Neural Information Processing Systems)

   Neural Radiance Fields (NeRF) have become an increasingly popular representation to capture high-quality appearance and shape of scenes and objects. However, learning generalizable NeRF priors over categories of scenes or objects has been challenging due to the high dimensionality of network weight space. To address the limitations of existing work on generalization, multi-view consistency and to improve quality, we propose HyP-NeRF, a latent conditioning method for learning generalizable category-level NeRF priors using hypernetworks. Rather than using hypernetworks to estimate only the weights of a NeRF, we estimate both the weights and the multi-resolution hash encodings resulting in significant quality gains. To improve quality even further, we incorporate a denoise and finetune strategy that denoises images rendered from NeRFs estimated by the hypernetwork and finetunes it while retaining multiview consistency. These improvements enable us to use HyP-NeRF as a generalizable prior for multiple downstream tasks including NeRF reconstruction from single-view or cluttered scenes and text-to-NeRF. We provide qualitative comparisons and evaluate HyP-NeRF on three tasks: generalization, compression, and retrieval, demonstrating our state-of-the-art results. 

   more » « less
2. HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork

   Sen, Bipasha; Singh, Gaurav; Agarwal, Aditya; Agaram, Rohith; MadhavaKrishna, K; Sridhar, Srinath (December 2023, NeurIPS 2023)

   Neural Radiance Fields (NeRF) have become an increasingly popular representation to capture high-quality appearance and shape of scenes and objects. However, learning generalizable NeRF priors over categories of scenes or objects has been challenging due to the high dimensionality of network weight space. To address the limitations of existing work on generalization, multi-view consistency and to improve quality, we propose HyP-NeRF, a latent conditioning method for learning generalizable category-level NeRF priors using hypernetworks. Rather than using hypernetworks to estimate only the weights of a NeRF, we estimate both the weights and the multi-resolution hash encodings resulting in significant quality gains. To improve quality even further, we incorporate a denoise and finetune strategy that denoises images rendered from NeRFs estimated by the hypernetwork and finetunes it while retaining multiview consistency. These improvements enable us to use HyP-NeRF as a generalizable prior for multiple downstream tasks including NeRF reconstruction from single-view or cluttered scenes and text-to-NeRF. We provide qualitative comparisons and evaluate HyP-NeRF on three tasks: generalization, compression, and retrieval, demonstrating our state-of-the-art results. 

   more » « less
3. Neural NeRF Compression

   Pham, T; Mandt, S (July 2024, International Conference for Machine Learning (ICML))
4. Neural NeRF Compression

   Pham, T; Mandt, S (July 2024, International Conference for Machine Learning)
5. SC-NeRF: NeRF-based Point Cloud Reconstruction using a Stationary Camera for Agricultural Applications

   Ku, Kibona; Jubery, Talukader; Rodriquez, Elijah; Balu, Aditya; Sarkar, Soumik; Krishnamurthy, Adarsh; Ganapathysubramanian, Baskar (June 2025, Computer Vision Foundation, CVPR Workshop)