Tiwari, AshishAshishTiwariRaman, ShanmuganathanShanmuganathanRaman2025-08-312025-08-312022-01-01[9781665405409]10.1109/ICASSP43922.2022.97469742-s2.0-85131246335http://repository.iitgn.ac.in/handle/IITG2025/26226Photometric stereo is a method to obtain surface normals of an object using its images captured under varying illumination directions. The existing deep learning-based methods require multiple images of an object captured using complex image acquisition systems. In this work, we propose a deep learning framework to perform three tasks jointly: (i) lighting estimation, (ii) image relighting, and (iii) surface normal estimation, all from a single input image of an object with non-Lambertian surface and general reflectance. The network explicitly segregates global geometric features and local lighting-specific features of the object from a single image. The local features resemble attached shadows, shadings, and specular highlights, providing valuable lighting estimation and relighting cues. The global features capture the lighting-independent geometric attributes that effectively guide the surface normal estimation. The joint training transfers valuable insights to achieve significant improvements across all three tasks. We show that the proposed single-image-based relighting framework outperforms several existing photometric stereo methods which require multiple images of a static object.falseImage-based Relighting | Photometric StereoConference Paper2060-2064202214cpConference Proceeding13