Dhawal Sirikonda

Recent Works

1. ISRF

   Interactive Segmentation of Radiance Fields

   Venue: CVPR ’23

   Rahul Goel*, Dhawal Sirikonda*, Saurabh Saini, and P. J. Narayanan

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023

   Abs Author Version Website

   Radiance Fields (RF) are popular to represent casually-captured scenes for new view generation and have been used for applications beyond it. Understanding and manipulating scenes represented as RFs have to naturally follow to facilitate mixed reality on personal spaces. Semantic segmentation of objects in the 3D scene is an important step for that. Prior segmentation efforts using feature distillation show promise but don’t scale to complex objects with diverse appearance. We present a framework to interactively segment objects with fine structure. Nearest neighbor feature matching identifies high-confidence regions of the objects using distilled features. Bilateral filtering in a joint spatio-semantic space grows the region to recover accurate segmentation. We show state-of-the-art results of segmenting objects from RFs and compositing them to another scene, changing appearance, etc., moving closer to rich scene manipulation and understanding.

2. PRTonAnySurf

   Real-Time Rendering of Arbitrary Surface Geometries using Learnt Transfer

   Venue: ICVGIP ’22

   Sirikonda Dhawal, Aakash KT, and P.J. Narayanan

   In Proceedings of the Thirteenth Indian Conference on Computer Vision, Graphics and Image Processing 2022

   AbsPublisher Version Website

   Precomputed Radiance Transfer (PRT) is widely used for real-time photorealistic effects. PRT disentangles the rendering equation into transfer and lighting, enabling their precomputation. Transfer accounts for the cosine-weighted visibility of points in the scene while lighting for emitted radiance from the environment. Prior art stored precomputed transfer in a tabulated manner, either in vertex or texture space. These values are fetched with interpolation at each point for shading. Vertex space methods require densely tessellated mesh vertices for high quality images. Texture space methods require non-overlapping and area-preserving UV mapping to be available. They also require a high-resolution texture to avoid rendering artifacts. In this paper, we propose a compact transfer representation that is learnt directly on scene geometry points. Specifically, we train a small multi-layer perceptron (MLP) to predict the transfer at sampled surface points. Our approach is most beneficial where inherent mesh storage structure and natural UV mapping are not available, such as Implicit Surfaces as it learns the transfer values directly on the surface. We demonstrate real-time, photorealistic renderings of diffuse and glossy materials on SDF geometries with PRT using our approach.

3. PRTonSDF

   Learnt Transfer for Surface Geometries

   Venue: High Performance Graphics (HPG) 2022-Poster

   Sirikonda Dhawal, Aakash KT, and P.J. Narayanan

   2022

   Publisher Version Website
4. TransferTextures

   Transfer Textures for Fast Precomputed Radiance Transfer

   Venue: EuroGraphics ’22

   Sirikonda Dhawal, Aakash Kt, and P. J. Narayanan

   In Eurographics 2022 - Posters 2022

   Publisher Version