Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Scanning large surface with PBR maps? No problem! Still polishing the methodologies and approach but initial tests are very promising. Here is a 130 x 50 cm tabletop, tricky reflective surface especially if we are aiming for smooth reconstruction.

18,326 Aufrufe • vor 1 Jahr •via X (Twitter)

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Facial reconstruction of a Neolithic man from Ukraine In 1949–1950, M. Ya. Rudinsky carried out excavations of a large Neolithic burial ground that he had discovered earlier, known as the Volnish burial ground. Based on the type of burials, the position of the skeletons, the grave goods, and the abundance of red ochre, this burial ground was closely related to the well-known Mariupol cemetery. As in the Mariupol burial ground, the burials here are arranged in dense rows, closely packed next to one another. The majority of the interments are accompanied by rich grave inventories. All skeletons lie on their backs, with the arms tightly pressed to the body and the legs extended. The inventory is represented by a large number of stone and bone tools. In addition, fish and animal bones were often found on and around the skeletons. The skull, densely covered in red ochre, was described by Mikhail Gerasimov as large and massive, with a very great cranial length of 196 mm, a small cranial breadth of 136 mm, and a wide cheek breadth of 142 mm. Mikhail Gerasimov describes the skull as follows: The brow ridges protrude strongly; their projection exceeds that of the glabella. The brow ridges are wide and fused with the upper margins of the orbits. The bases of the zygomatic arches are wide. The zygomatic processes of the temporal bones are massive. The temporal lines are very well developed. The mastoid processes are very large and wide; their surface is flat. The occipital bone is long, very narrow, and laterally compressed in the area of the superior nuchal line. The occipital protuberance is weakly expressed; it is rounded and has a smooth surface. The face is pentagonal in shape, very high, with wide and massive cheekbones and strongly protruding angles of the heavy lower jaw; it is strongly profiled. The nasal bridge is high. The orbits are small. The alveolar part is low and orthognathic. The chin is strongly projecting. The orbits are rectangular, with strongly rounded corners. The orbital margins are thickened. The lower orbital margins are elevated. The eye sockets are closed. The lacrimal fossae are deepened. The supraorbital tubercles are weakly expressed and represented by broad, flat surfaces. The inclination of the palpebral fissure is slight. The frontal orientation of the orbits is elevated. The orbital profile is inclined. The zygomatic bones are massive and very wide. The lower portions of the zygomatic bones are displaced forward and elevated. The zygomatic tubercles are strongly developed. The frontal processes of the zygomatic bones are wide and flat. The canine fossae are weakly expressed. The areas for muscle attachment are well developed. The maxillary notches are deep. The alveolar part is very low (12 mm) and orthognathic. The teeth are wide and short, set orthognathically. The height of the first incisor is 6.5 mm. Wear on the incisors and canines has reached complete cross-section of the tooth. The mandible is large, with strongly developed angles, and is very massive. The body of the mandible is very high. The horizontal rami are weakly flared. The mental protuberance reaches 9 points on the scale. The rami of the mandible are very wide and high and diverge at a right angle. The mandibular angles are rounded and strongly everted, with a pronounced crest. The coronoid processes of the mandible are also everted. In terms of its anthropological characteristics, this represents the same type that is already well known to us from skulls from Murzak-Koba, Sursky Island (Type A), and Vinogradny Island. Since the archaeological material has not yet been published, we are currently deprived of the opportunity to precisely establish the chronological position of this individual. If we assume that this burial ground dates to the same period as the early burials of the Mariupol cemetery, then it belongs to the period of the developed Neolithic stage. This gives us the right to state that the anthropological type of ancient Cro-Magnons was conservatively preserved in remote regions up until the 4th–3rd millennia BC. Apparently, survivals of this same anthropological type can also be traced in the skulls of the Yamnaya culture of this region.

Ancestral Whispers

53,384 Aufrufe • vor 6 Monaten

Two weeks ago I fixed one of my teeth with algorithms I wrote a couple of years ago! I got hooked by 3D scanning when I started to work for a software shop in Zurich that was programming 3D computational geometry algorithms for denture scanning to produce crowns (and more). Back then, a typical reconstruction pipeline was like: scan the patient’s teeth using an intraoral scanner, reconstruct the surface mesh, design the restoration digitally, and finally mill the crown out of ceramic. We were working mostly with point clouds and meshes, but it wasn’t just math, it was craftsmanship translated into a digital process. Every micron mattered. You could literally see how a good algorithm meant a better fit in someone’s mouth. Gaussian Splatting isn’t about surface reconstruction, it’s about appearance reconstruction. It doesn’t care about explicit topology, it captures how light interacts with the scene. In a sense, it’s the opposite philosophy of the dental world: instead of modeling what the object is, it models how the object looks. 3D Gaussian Splatting enables applications like training self driving cars, teaching robots to understand their environment, creating virtual worlds, or monitoring real sites. It represents scenes as millions of small Gaussians rendered in real time without the need for meshes or textures. Coming from a world where precision geometry was everything, this shift felt natural. It’s still about reconstruction, but with a different goal: not manufacturing a perfect object, but reproducing how the world actually looks. Two weeks ago I got my first dental crown, made with the same software, reconstruction algorithms, and Swiss precision I once helped develop. I haven’t worked there in two years, but sitting in that chair and seeing the process from the other side was a proud moment. It reminded me why I love this field.

MrNeRF

289,948 Aufrufe • vor 8 Monaten