Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟳𝟮 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗼𝘂𝘀 𝗢𝗯𝗷𝗲𝗰𝘁 𝗥𝗲𝗽𝗿𝗲𝘀𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 𝗡𝗲𝘁𝘄𝗼𝗿𝗸𝘀: Novel View Synthesis without Target View Supervision by University of Minnesota Follow me for a similar post: 🇮🇳 Ashish Patel Interesting Facts : 🔸 This paper is published #NeuroIPS2020 with 5 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/ewj7e9sC Code: https://lnkd.in/ehR-QugK ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Novel View Synthesis (NVS) is concerned with synthesizing views under camera viewpoint transformations from one or multiple input images.  🔸 NVS requires explicit reasoning about 3D object structure and unseen parts of the scene to synthesize convincing results. As a result, current approaches typically rely on supervised training with either ground truth 3D models or multiple target images.  🔸 We propose Continuous Object Representation Networks (CORN), a conditional architecture that encodes an input image's geometry and appearance that map to a 3D consistent scene representation. We can train CORN with only two source images per object by combining our model with a neural renderer.  🔸 A key feature of CORN is that it requires no ground truth 3D models or target view supervision. Regardless, CORN performs well on challenging tasks such as novel view synthesis and single-view 3D reconstruction and achieves performance comparable to state-of-the-art approaches that use direct supervision.  #computervision #artificialintelligence #innovation