SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimates

Figure 1 . SCADE Overview. We present SCADE, a novel technique for NeRF reconstruction under sparse, unconstrained views for in-the-wild indoor scenes. We leverage on generalizable monocular depth priors and address to represent the inherent ambiguities of monocular depth by exploiting our ambiguity-aware depth estimates (left). Our approach accounts for multimodality of both distributions using our novel space carving loss that seeks to disambiguate and find the common mode to fuse the information between different views (middle). SCADE enables better photometric reconstruction especially in highly ambiguous scenes, e.g. non-opaque surfaces (right).