We present a novel method for capturing real-world, spatially-varying surface reflectance from a small number of object views ( k ). Our key observation is that a specific target's reflectance can be represented by a small number of custom basis materials ( N ) convexly blended by an even smaller number of non-zero weights at each point ( n ). Based on this sparse basis/sparser blend model, we develop an SVBRDF reconstruction algorithm that jointly solves for n , N , the basis BRDFs, and their spatial blend weights with an alternating iterative optimization, each step of which solves a linearly-constrained quadratic programming problem. We develop a numerical tool that lets us estimate the number of views required and analyze the effect of lighting and geometry on reconstruction quality. We validate our method with images rendered from synthetic BRDFs, and demonstrate convincing results on real objects of pre-scanned shape and lit by uncontrolled natural illumination, from very few or even a single input image.

No abstract

We present deferred neural lighting, a novel method for free-viewpoint relighting from unstructured photographs of a scene captured with handheld devices. Our method leverages a scene-dependent neural rendering network for relighting a rough geometric proxy with learnable neural textures. Key to making the rendering network lighting aware are radiance cues: global illumination renderings of a rough proxy geometry of the scene for a small set of basis materials and lit by the target lighting. As such, the light transport through the scene is never explicitely modeled, but resolved at rendering time by a neural rendering network. We demonstrate that the neural textures and neural renderer can be trained end-to-end from unstructured photographs captured with a double hand-held camera setup that concurrently captures the scene while being lit by only one of the cameras' flash lights. In addition, we propose a novel augmentation refinement strategy that exploits the linearity of light transport to extend the relighting capabilities of the neural rendering network to support other lighting types (e.g., environment lighting) beyond the lighting used during acquisition (i.e., flash lighting). We demonstrate our deferred neural lighting solution on a variety of real-world and synthetic scenes exhibiting a wide range of material properties, light transport effects, and geometrical complexity.

For the path planning and obstacle avoidance problem of mobile robots in unknown surroundings, a novel improved artificial potential field (IAPF) model was proposed in this study. In order to overcome the shortages of low efficiency, local optimization trap, and unreachable target in the classical artificial potential field (APF) method, the new adaptive step length adjustment strategy was proposed in IAPF, which improved the path planning and obstacle avoidance efficiency. A new triangular navigation method was designed to solve the local optimization trap in joint force zero condition for a variety of path planning. In order to solve the target unreachable problem, a new target attraction model was established based on the distance of obstacle to improve convergence rate, and the new method was designed such as adding the aim factor to optimize the rejection force function and so on. The two methods of IAPF and APF are compared using MATLAB simulation, the average path planning efficiency of IAPF is increased by 42.8% compared with APF, the average path length is reduced by 8.6%, and the average target convergence rate is increased by 26.1%. Finally, the physical test of the mobile robot verified the effectiveness and accuracy of IAPF.